{"id":15623,"date":"2024-01-14T19:45:14","date_gmt":"2024-01-14T16:15:14","guid":{"rendered":"https:\/\/rasanegar.com\/blog\/%d8%b1%d8%a7%d9%87%d9%86%d9%85%d8%a7%db%8c-%d8%aa%d8%ac%d8%b2%db%8c%d9%87-html-%d8%a8%d8%a7-beautifulsoup-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86\/"},"modified":"2024-01-14T19:45:14","modified_gmt":"2024-01-14T16:15:14","slug":"%d8%b1%d8%a7%d9%87%d9%86%d9%85%d8%a7%db%8c-%d8%aa%d8%ac%d8%b2%db%8c%d9%87-html-%d8%a8%d8%a7-beautifulsoup-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86","status":"publish","type":"post","link":"https:\/\/rasanegaar.com\/blog\/%d8%b1%d8%a7%d9%87%d9%86%d9%85%d8%a7%db%8c-%d8%aa%d8%ac%d8%b2%db%8c%d9%87-html-%d8%a8%d8%a7-beautifulsoup-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86\/","title":{"rendered":"\u0631\u0627\u0647\u0646\u0645\u0627\u06cc \u062a\u062c\u0632\u06cc\u0647 HTML \u0628\u0627 BeautifulSoup \u062f\u0631 \u067e\u0627\u06cc\u062a\u0648\u0646"},"content":{"rendered":"<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_85 counter-hierarchy ez-toc-counter ez-toc-custom ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\"><p class=\"ez-toc-title\" style=\"cursor:inherit\">\u0633\u0631\u0641\u0635\u0644\u0647\u0627\u06cc \u0645\u0637\u0644\u0628<\/p>\n<\/div><nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/rasanegaar.com\/blog\/%d8%b1%d8%a7%d9%87%d9%86%d9%85%d8%a7%db%8c-%d8%aa%d8%ac%d8%b2%db%8c%d9%87-html-%d8%a8%d8%a7-beautifulsoup-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86\/#%d9%85%d8%b9%d8%b1%d9%81%db%8c\" >\u0645\u0639\u0631\u0641\u06cc<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/rasanegaar.com\/blog\/%d8%b1%d8%a7%d9%87%d9%86%d9%85%d8%a7%db%8c-%d8%aa%d8%ac%d8%b2%db%8c%d9%87-html-%d8%a8%d8%a7-beautifulsoup-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86\/#%d8%ae%d8%b1%d8%a7%d8%b4_%d8%af%d8%a7%d8%af%d9%86_%d9%88%d8%a8_%d8%a7%d8%ae%d9%84%d8%a7%d9%82%db%8c\" >\u062e\u0631\u0627\u0634 \u062f\u0627\u062f\u0646 \u0648\u0628 \u0627\u062e\u0644\u0627\u0642\u06cc<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/rasanegaar.com\/blog\/%d8%b1%d8%a7%d9%87%d9%86%d9%85%d8%a7%db%8c-%d8%aa%d8%ac%d8%b2%db%8c%d9%87-html-%d8%a8%d8%a7-beautifulsoup-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86\/#%d9%85%d8%b1%d9%88%d8%b1%db%8c_%d8%a8%d8%b1_%d8%b3%d9%88%d9%be_%d8%b2%db%8c%d8%a8%d8%a7\" >\u0645\u0631\u0648\u0631\u06cc \u0628\u0631 \u0633\u0648\u067e \u0632\u06cc\u0628\u0627<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/rasanegaar.com\/blog\/%d8%b1%d8%a7%d9%87%d9%86%d9%85%d8%a7%db%8c-%d8%aa%d8%ac%d8%b2%db%8c%d9%87-html-%d8%a8%d8%a7-beautifulsoup-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86\/#%d9%be%db%8c%d9%85%d8%a7%db%8c%d8%b4_%d8%a8%d9%87_%d8%a8%d8%b1%da%86%d8%b3%d8%a8_%d9%87%d8%a7%db%8c_%d8%ae%d8%a7%d8%b5\" >\u067e\u06cc\u0645\u0627\u06cc\u0634 \u0628\u0647 \u0628\u0631\u0686\u0633\u0628 \u0647\u0627\u06cc \u062e\u0627\u0635<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/rasanegaar.com\/blog\/%d8%b1%d8%a7%d9%87%d9%86%d9%85%d8%a7%db%8c-%d8%aa%d8%ac%d8%b2%db%8c%d9%87-html-%d8%a8%d8%a7-beautifulsoup-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86\/#%d8%ac%d8%b3%d8%aa%d8%ac%d9%88_%d8%af%d8%b1_%d8%b9%d9%86%d8%a7%d8%b5%d8%b1_%d8%a8%d8%b1%da%86%d8%b3%d8%a8_%d9%87%d8%a7\" >\u062c\u0633\u062a\u062c\u0648 \u062f\u0631 \u0639\u0646\u0627\u0635\u0631 \u0628\u0631\u0686\u0633\u0628 \u0647\u0627<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/rasanegaar.com\/blog\/%d8%b1%d8%a7%d9%87%d9%86%d9%85%d8%a7%db%8c-%d8%aa%d8%ac%d8%b2%db%8c%d9%87-html-%d8%a8%d8%a7-beautifulsoup-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86\/#%d8%af%d8%b1%db%8c%d8%a7%d9%81%d8%aa_%da%a9%d9%84_%d9%85%d8%aa%d9%86\" >\u062f\u0631\u06cc\u0627\u0641\u062a \u06a9\u0644 \u0645\u062a\u0646<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/rasanegaar.com\/blog\/%d8%b1%d8%a7%d9%87%d9%86%d9%85%d8%a7%db%8c-%d8%aa%d8%ac%d8%b2%db%8c%d9%87-html-%d8%a8%d8%a7-beautifulsoup-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86\/#%d8%b3%d9%88%d9%be_%d8%b2%db%8c%d8%a8%d8%a7_%d8%af%d8%b1_%d8%b9%d9%85%d9%84_%e2%80%93_%d8%aa%d9%87%db%8c%d9%87_%d9%81%d9%87%d8%b1%d8%b3%d8%aa_%da%a9%d8%aa%d8%a7%d8%a8\" >\u0633\u0648\u067e \u0632\u06cc\u0628\u0627 \u062f\u0631 \u0639\u0645\u0644 &#8211; \u062a\u0647\u06cc\u0647 \u0641\u0647\u0631\u0633\u062a \u06a9\u062a\u0627\u0628<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/rasanegaar.com\/blog\/%d8%b1%d8%a7%d9%87%d9%86%d9%85%d8%a7%db%8c-%d8%aa%d8%ac%d8%b2%db%8c%d9%87-html-%d8%a8%d8%a7-beautifulsoup-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86\/#%d9%86%d8%aa%db%8c%d8%ac%d9%87\" >\u0646\u062a\u06cc\u062c\u0647<\/a><\/li><\/ul><\/nav><\/div>\n<span class=\"span-reading-time rt-reading-time\" style=\"display: block;\"><span class=\"rt-label rt-prefix\">\u0632\u0645\u0627\u0646 \u0644\u0627\u0632\u0645 \u0628\u0631\u0627\u06cc \u0645\u0637\u0627\u0644\u0639\u0647: <\/span> <span class=\"rt-time\"> 7<\/span> <span class=\"rt-label rt-postfix\">\u062f\u0642\u06cc\u0642\u0647<\/span><\/span><p> <br \/>\n<\/p>\n<div><noscript><\/noscript><\/p>\n<h2 id=\"introduction\"><span class=\"ez-toc-section\" id=\"%d9%85%d8%b9%d8%b1%d9%81%db%8c\"><\/span>\u0645\u0639\u0631\u0641\u06cc<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Web scraping \u0628\u0647 \u0635\u0648\u0631\u062a \u0628\u0631\u0646\u0627\u0645\u0647 \u0646\u0648\u06cc\u0633\u06cc \u0627\u0637\u0644\u0627\u0639\u0627\u062a \u0631\u0627 \u0627\u0632 \u0648\u0628 \u0633\u0627\u06cc\u062a \u0647\u0627\u06cc \u0645\u062e\u062a\u0644\u0641 \u062c\u0645\u0639 \u0622\u0648\u0631\u06cc \u0645\u06cc \u06a9\u0646\u062f.  \u062f\u0631 \u062d\u0627\u0644\u06cc \u06a9\u0647 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647\u200c\u0647\u0627 \u0648 \u0686\u0627\u0631\u0686\u0648\u0628\u200c\u0647\u0627\u06cc \u0632\u06cc\u0627\u062f\u06cc \u0628\u0647 \u0632\u0628\u0627\u0646\u200c\u0647\u0627\u06cc \u0645\u062e\u062a\u0644\u0641 \u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f \u06a9\u0647 \u0645\u06cc\u200c\u062a\u0648\u0627\u0646\u0646\u062f \u062f\u0627\u062f\u0647\u200c\u0647\u0627\u06cc \u0648\u0628 \u0631\u0627 \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u06a9\u0646\u0646\u062f\u060c \u067e\u0627\u06cc\u062a\u0648\u0646 \u0628\u0647 \u062f\u0644\u06cc\u0644 \u06af\u0632\u06cc\u0646\u0647\u200c\u0647\u0627\u06cc \u0641\u0631\u0627\u0648\u0627\u0646\u06cc \u06a9\u0647 \u0628\u0631\u0627\u06cc \u0627\u0633\u06a9\u0631\u067e\u06cc\u0646\u06af \u0648\u0628 \u062f\u0627\u0631\u062f\u060c \u0645\u062f\u062a\u200c\u0647\u0627\u0633\u062a \u06a9\u0647 \u06cc\u06a9 \u0627\u0646\u062a\u062e\u0627\u0628 \u0645\u062d\u0628\u0648\u0628 \u0628\u0648\u062f\u0647 \u0627\u0633\u062a.<\/p>\n<p>\u0627\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647 \u0628\u0647 \u0634\u0645\u0627 \u06cc\u06a9 \u062f\u0648\u0631\u0647 \u062a\u0635\u0627\u062f\u0641 \u0645\u06cc \u062f\u0647\u062f \u0631\u0648\u06cc \u062e\u0631\u0627\u0634 \u062f\u0627\u062f\u0646 \u0648\u0628 \u062f\u0631 \u067e\u0627\u06cc\u062a\u0648\u0646 \u0628\u0627 <em>\u0633\u0648\u067e \u0632\u06cc\u0628\u0627<\/em> &#8211; \u06cc\u06a9 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0645\u062d\u0628\u0648\u0628 \u067e\u0627\u06cc\u062a\u0648\u0646 \u0628\u0631\u0627\u06cc \u062a\u062c\u0632\u06cc\u0647 HTML \u0648 XML.<\/p>\n<h2 id=\"ethicalwebscraping\"><span class=\"ez-toc-section\" id=\"%d8%ae%d8%b1%d8%a7%d8%b4_%d8%af%d8%a7%d8%af%d9%86_%d9%88%d8%a8_%d8%a7%d8%ae%d9%84%d8%a7%d9%82%db%8c\"><\/span>\u062e\u0631\u0627\u0634 \u062f\u0627\u062f\u0646 \u0648\u0628 \u0627\u062e\u0644\u0627\u0642\u06cc<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>\u0627\u0633\u06a9\u0631\u067e\u06cc\u0646\u06af \u0648\u0628 \u0647\u0645\u0647 \u062c\u0627 \u062d\u0627\u0636\u0631 \u0627\u0633\u062a \u0648 \u062f\u0627\u062f\u0647 \u0647\u0627\u06cc\u06cc \u0631\u0627 \u0628\u0647 \u0645\u0627 \u0645\u06cc \u062f\u0647\u062f \u06a9\u0647 \u0628\u0627 \u06cc\u06a9 API \u062f\u0631\u06cc\u0627\u0641\u062a \u0645\u06cc \u06a9\u0646\u06cc\u0645.  \u0628\u0627 \u0627\u06cc\u0646 \u062d\u0627\u0644\u060c \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0634\u0647\u0631\u0648\u0646\u062f\u0627\u0646 \u062e\u0648\u0628 \u0627\u06cc\u0646\u062a\u0631\u0646\u062a\u060c \u0627\u06cc\u0646 \u0645\u0633\u0626\u0648\u0644\u06cc\u062a \u0645\u0627\u0633\u062a \u06a9\u0647 \u0628\u0647 \u0635\u0627\u062d\u0628\u0627\u0646 \u0633\u0627\u06cc\u062a\u06cc \u06a9\u0647 \u0627\u0632 \u0622\u0646\u0647\u0627 \u0645\u06cc \u062e\u0631\u06cc\u0645 \u0627\u062d\u062a\u0631\u0627\u0645 \u0628\u06af\u0630\u0627\u0631\u06cc\u0645.  \u062f\u0631 \u0627\u06cc\u0646\u062c\u0627 \u0686\u0646\u062f \u0627\u0635\u0644 \u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f \u06a9\u0647 \u06cc\u06a9 \u0648\u0628 \u0627\u0633\u06a9\u0631\u0627\u067e\u0631 \u0628\u0627\u06cc\u062f \u0628\u0647 \u0622\u0646\u0647\u0627 \u067e\u0627\u06cc\u0628\u0646\u062f \u0628\u0627\u0634\u062f:<\/p>\n<ul>\n<li>\u0645\u062d\u062a\u0648\u0627\u06cc \u062e\u0631\u0627\u0634\u06cc\u062f\u0647 \u0634\u062f\u0647 \u0631\u0627 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0645\u062d\u062a\u0648\u0627\u06cc \u0645\u0627 \u0627\u062f\u0639\u0627 \u0646\u06a9\u0646\u06cc\u062f.  \u0635\u0627\u062d\u0628\u0627\u0646 \u0648\u0628\u200c\u0633\u0627\u06cc\u062a\u200c\u0647\u0627 \u06af\u0627\u0647\u06cc \u0627\u0648\u0642\u0627\u062a \u0632\u0645\u0627\u0646 \u0632\u06cc\u0627\u062f\u06cc \u0631\u0627 \u0635\u0631\u0641 \u0627\u06cc\u062c\u0627\u062f \u0645\u0642\u0627\u0644\u0647\u060c \u062c\u0645\u0639\u200c\u0622\u0648\u0631\u06cc \u062c\u0632\u0626\u06cc\u0627\u062a \u062f\u0631\u0628\u0627\u0631\u0647 \u0645\u062d\u0635\u0648\u0644\u0627\u062a \u06cc\u0627 \u062c\u0645\u0639\u200c\u0622\u0648\u0631\u06cc \u0645\u062d\u062a\u0648\u0627\u06cc \u062f\u06cc\u06af\u0631 \u0645\u06cc\u200c\u06a9\u0646\u0646\u062f.  \u0645\u0627 \u0628\u0627\u06cc\u062f \u0628\u0647 \u0632\u062d\u0645\u062a \u0648 \u0627\u0635\u0627\u0644\u062a \u0622\u0646\u0647\u0627 \u0627\u062d\u062a\u0631\u0627\u0645 \u0628\u06af\u0630\u0627\u0631\u06cc\u0645.<\/li>\n<li>\u0648\u0628 \u0633\u0627\u06cc\u062a\u06cc \u0631\u0627 \u06a9\u0647 \u0646\u0645\u06cc \u062e\u0648\u0627\u0647\u062f \u062e\u0631\u0627\u0634\u06cc\u062f\u0647 \u0634\u0648\u062f\u060c \u062e\u0631\u0627\u0634 \u0646\u062f\u0647\u06cc\u062f.  \u0648\u0628 \u0633\u0627\u06cc\u062a \u0647\u0627 \u06af\u0627\u0647\u06cc \u0627\u0648\u0642\u0627\u062a \u0628\u0627 \u06cc\u06a9 <code>robots.txt<\/code> \u0641\u0627\u06cc\u0644 &#8211; \u06a9\u0647 \u0642\u0633\u0645\u062a \u0647\u0627\u06cc\u06cc \u0627\u0632 \u06cc\u06a9 \u0648\u0628 \u0633\u0627\u06cc\u062a \u0631\u0627 \u06a9\u0647 \u0645\u06cc \u062a\u0648\u0627\u0646 \u062e\u0631\u0627\u0634 \u062f\u0627\u062f \u0631\u0627 \u062a\u0639\u0631\u06cc\u0641 \u0645\u06cc \u06a9\u0646\u062f.  \u0628\u0633\u06cc\u0627\u0631\u06cc \u0627\u0632 \u0648\u0628 \u0633\u0627\u06cc\u062a \u0647\u0627 \u0647\u0645\u0686\u0646\u06cc\u0646 \u0634\u0631\u0627\u06cc\u0637 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u062f\u0627\u0631\u0646\u062f \u06a9\u0647 \u0645\u0645\u06a9\u0646 \u0627\u0633\u062a \u0627\u062c\u0627\u0632\u0647 \u062e\u0631\u0627\u0634 \u062f\u0627\u062f\u0646 \u0631\u0627 \u0646\u062f\u0647\u0646\u062f.  \u0645\u0627 \u0628\u0627\u06cc\u062f \u0628\u0647 \u0648\u0628 \u0633\u0627\u06cc\u062a \u0647\u0627\u06cc\u06cc \u06a9\u0647 \u0646\u0645\u06cc \u062e\u0648\u0627\u0647\u0646\u062f \u062e\u0631\u0627\u0634\u06cc\u062f\u0647 \u0634\u0648\u0646\u062f \u0627\u062d\u062a\u0631\u0627\u0645 \u0628\u06af\u0630\u0627\u0631\u06cc\u0645.<\/li>\n<li>\u0622\u06cc\u0627 API \u062f\u0631 \u062d\u0627\u0644 \u062d\u0627\u0636\u0631 \u0645\u0648\u062c\u0648\u062f \u0627\u0633\u062a\u061f  \u0628\u0633\u06cc\u0627\u0631 \u0639\u0627\u0644\u06cc\u060c \u0646\u06cc\u0627\u0632\u06cc \u0628\u0647 \u0646\u0648\u0634\u062a\u0646 \u0627\u0633\u06a9\u0631\u0627\u067e\u0631 \u0646\u06cc\u0633\u062a.  API\u0647\u0627 \u0628\u0631\u0627\u06cc \u0641\u0631\u0627\u0647\u0645 \u06a9\u0631\u062f\u0646 \u062f\u0633\u062a\u0631\u0633\u06cc \u0628\u0647 \u062f\u0627\u062f\u0647 \u0647\u0627 \u0628\u0647 \u0631\u0648\u0634\u06cc \u06a9\u0646\u062a\u0631\u0644 \u0634\u062f\u0647 \u06a9\u0647 \u062a\u0648\u0633\u0637 \u0635\u0627\u062d\u0628\u0627\u0646 \u062f\u0627\u062f\u0647 \u0647\u0627 \u062a\u0639\u0631\u06cc\u0641 \u0634\u062f\u0647 \u0627\u0633\u062a \u0627\u06cc\u062c\u0627\u062f \u0645\u06cc \u0634\u0648\u0646\u062f.  \u0645\u0627 \u062a\u0631\u062c\u06cc\u062d \u0645\u06cc \u062f\u0647\u06cc\u0645 \u0627\u0632 API \u0647\u0627 \u062f\u0631 \u0635\u0648\u0631\u062a \u062f\u0631 \u062f\u0633\u062a\u0631\u0633 \u0628\u0648\u062f\u0646 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0646\u06cc\u0645.<\/li>\n<li>\u062f\u0631\u062e\u0648\u0627\u0633\u062a \u0628\u0631\u0627\u06cc \u06cc\u06a9 \u0648\u0628 \u0633\u0627\u06cc\u062a \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u0628\u0627\u0639\u062b \u0639\u0648\u0627\u0631\u0636 \u0634\u0648\u062f \u0631\u0648\u06cc \u0639\u0645\u0644\u06a9\u0631\u062f \u06cc\u06a9 \u0648\u0628 \u0633\u0627\u06cc\u062a  \u06cc\u06a9 \u0627\u0633\u06a9\u0631\u0627\u067e\u0631 \u0648\u0628 \u06a9\u0647 \u062f\u0631\u062e\u0648\u0627\u0633\u062a \u0647\u0627\u06cc \u0632\u06cc\u0627\u062f\u06cc \u0645\u06cc \u06a9\u0646\u062f \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u0628\u0647 \u0627\u0646\u062f\u0627\u0632\u0647 \u06cc\u06a9 \u062d\u0645\u0644\u0647 DDOS \u0636\u0639\u06cc\u0641 \u06a9\u0646\u0646\u062f\u0647 \u0628\u0627\u0634\u062f.  \u0645\u0627 \u0628\u0627\u06cc\u062f \u0628\u0647 \u0637\u0648\u0631 \u0645\u0633\u0626\u0648\u0644\u0627\u0646\u0647 \u062e\u0631\u0627\u0634 \u062f\u0647\u06cc\u0645 \u062a\u0627 \u0647\u06cc\u0686 \u06af\u0648\u0646\u0647 \u0627\u062e\u062a\u0644\u0627\u0644\u06cc \u062f\u0631 \u0639\u0645\u0644\u06a9\u0631\u062f \u0645\u0646\u0638\u0645 \u0648\u0628 \u0633\u0627\u06cc\u062a \u0627\u06cc\u062c\u0627\u062f \u0646\u06a9\u0646\u06cc\u0645.<\/li>\n<\/ul>\n<h2 id=\"anoverviewofbeautifulsoup\"><span class=\"ez-toc-section\" id=\"%d9%85%d8%b1%d9%88%d8%b1%db%8c_%d8%a8%d8%b1_%d8%b3%d9%88%d9%be_%d8%b2%db%8c%d8%a8%d8%a7\"><\/span>\u0645\u0631\u0648\u0631\u06cc \u0628\u0631 \u0633\u0648\u067e \u0632\u06cc\u0628\u0627<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>\u0645\u062d\u062a\u0648\u0627\u06cc HTML \u0635\u0641\u062d\u0627\u062a \u0648\u0628 \u0631\u0627 \u0645\u06cc \u062a\u0648\u0627\u0646 \u0628\u0627 Beautiful Soup \u062a\u062c\u0632\u06cc\u0647 \u0648 \u062a\u062d\u0644\u06cc\u0644 \u06a9\u0631\u062f.  \u062f\u0631 \u0628\u062e\u0634 \u0628\u0639\u062f\u06cc\u060c \u0639\u0645\u0644\u06a9\u0631\u062f\u0647\u0627\u06cc\u06cc \u0631\u0627 \u06a9\u0647 \u0628\u0631\u0627\u06cc \u062e\u0631\u0627\u0634 \u062f\u0627\u062f\u0646 \u0635\u0641\u062d\u0627\u062a \u0648\u0628 \u0645\u0641\u06cc\u062f \u0647\u0633\u062a\u0646\u062f\u060c \u067e\u0648\u0634\u0634 \u062e\u0648\u0627\u0647\u06cc\u0645 \u062f\u0627\u062f.<\/p>\n<p>\u0686\u06cc\u0632\u06cc \u06a9\u0647 Beautiful Soup \u0631\u0627 \u0628\u0633\u06cc\u0627\u0631 \u0645\u0641\u06cc\u062f \u0645\u06cc \u06a9\u0646\u062f\u060c \u062a\u0648\u0627\u0628\u0639 \u0628\u06cc \u0634\u0645\u0627\u0631\u06cc \u0627\u0633\u062a \u06a9\u0647 \u0628\u0631\u0627\u06cc \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u062f\u0627\u062f\u0647 \u0647\u0627 \u0627\u0632 HTML \u0627\u0631\u0627\u0626\u0647 \u0645\u06cc \u062f\u0647\u062f.  \u0627\u06cc\u0646 \u062a\u0635\u0648\u06cc\u0631 \u0632\u06cc\u0631 \u0628\u0631\u062e\u06cc \u0627\u0632 \u0639\u0645\u0644\u06a9\u0631\u062f\u0647\u0627\u06cc\u06cc \u0631\u0627 \u06a9\u0647 \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u0645 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0646\u06cc\u0645 \u0631\u0627 \u0646\u0634\u0627\u0646 \u0645\u06cc \u062f\u0647\u062f:<\/p>\n<p><img decoding=\"async\" src=\"https:\/\/rasanegar.com\/blog\/wp-content\/uploads\/2024\/01\/parsing-html-with-beautifulsoup-in-python-1.jpg\" alt=\"BeautifulSoup - \u06cc\u06a9 \u0645\u0631\u0648\u0631 \u06a9\u0644\u06cc\" title=\"\"><\/p>\n<p>\u0628\u06cc\u0627 \u062f\u0633\u062a \u0628\u06af\u06cc\u0631\u06cc\u0645 -\u0631\u0648\u06cc \u0648 \u0628\u0628\u06cc\u0646\u06cc\u062f \u0686\u06af\u0648\u0646\u0647 \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u0645 HTML \u0631\u0627 \u0628\u0627 Beautiful Soup \u062a\u062c\u0632\u06cc\u0647 \u06a9\u0646\u06cc\u0645.  HTML \u0632\u06cc\u0631 \u0631\u0627 \u062f\u0631 \u0646\u0638\u0631 \u0628\u06af\u06cc\u0631\u06cc\u062f page \u062f\u0631 \u0641\u0627\u06cc\u0644 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0630\u062e\u06cc\u0631\u0647 \u0634\u062f <code>doc.html<\/code>:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-tag\">&lt;<span class=\"hljs-name\">html<\/span>&gt;<\/span>\n<span class=\"hljs-tag\">&lt;<span class=\"hljs-name\">head<\/span>&gt;<\/span>\n  <span class=\"hljs-tag\">&lt;<span class=\"hljs-name\">title<\/span>&gt;<\/span>Head's title<span class=\"hljs-tag\">&lt;\/<span class=\"hljs-name\">title<\/span>&gt;<\/span>\n<span class=\"hljs-tag\">&lt;\/<span class=\"hljs-name\">head<\/span>&gt;<\/span>\n\n<span class=\"hljs-tag\">&lt;<span class=\"hljs-name\">body<\/span>&gt;<\/span>\n  <span class=\"hljs-tag\">&lt;<span class=\"hljs-name\">p<\/span> <span class=\"hljs-attr\">class<\/span>=<span class=\"hljs-string\">\"title\"<\/span>&gt;<\/span><span class=\"hljs-tag\">&lt;<span class=\"hljs-name\">b<\/span>&gt;<\/span>Body's title<span class=\"hljs-tag\">&lt;\/<span class=\"hljs-name\">b<\/span>&gt;<\/span><span class=\"hljs-tag\">&lt;\/<span class=\"hljs-name\">p<\/span>&gt;<\/span>\n  <span class=\"hljs-tag\">&lt;<span class=\"hljs-name\">p<\/span> <span class=\"hljs-attr\">class<\/span>=<span class=\"hljs-string\">\"story\"<\/span>&gt;<\/span>Line begins\n    <span class=\"hljs-tag\">&lt;<span class=\"hljs-name\">a<\/span> <span class=\"hljs-attr\">href<\/span>=<span class=\"hljs-string\">\"http:\/\/example.com\/element1\"<\/span> <span class=\"hljs-attr\">class<\/span>=<span class=\"hljs-string\">\"element\"<\/span> <span class=\"hljs-attr\">id<\/span>=<span class=\"hljs-string\">\"link1\"<\/span>&gt;<\/span>1<span class=\"hljs-tag\">&lt;\/<span class=\"hljs-name\">a<\/span>&gt;<\/span>\n    <span class=\"hljs-tag\">&lt;<span class=\"hljs-name\">a<\/span> <span class=\"hljs-attr\">href<\/span>=<span class=\"hljs-string\">\"http:\/\/example.com\/element2\"<\/span> <span class=\"hljs-attr\">class<\/span>=<span class=\"hljs-string\">\"element\"<\/span> <span class=\"hljs-attr\">id<\/span>=<span class=\"hljs-string\">\"link2\"<\/span>&gt;<\/span>2<span class=\"hljs-tag\">&lt;\/<span class=\"hljs-name\">a<\/span>&gt;<\/span>\n    <span class=\"hljs-tag\">&lt;<span class=\"hljs-name\">a<\/span> <span class=\"hljs-attr\">href<\/span>=<span class=\"hljs-string\">\"http:\/\/example.com\/avatar1\"<\/span> <span class=\"hljs-attr\">class<\/span>=<span class=\"hljs-string\">\"avatar\"<\/span> <span class=\"hljs-attr\">id<\/span>=<span class=\"hljs-string\">\"link3\"<\/span>&gt;<\/span>3<span class=\"hljs-tag\">&lt;\/<span class=\"hljs-name\">a<\/span>&gt;<\/span>\n  <span class=\"hljs-tag\">&lt;<span class=\"hljs-name\">p<\/span>&gt;<\/span> line ends<span class=\"hljs-tag\">&lt;\/<span class=\"hljs-name\">p<\/span>&gt;<\/span>\n<span class=\"hljs-tag\">&lt;\/<span class=\"hljs-name\">body<\/span>&gt;<\/span>\n<span class=\"hljs-tag\">&lt;\/<span class=\"hljs-name\">html<\/span>&gt;<\/span>\n<\/code><\/pre>\n<p>\u0642\u0637\u0639\u0647 \u06a9\u062f \u0632\u06cc\u0631 \u062a\u0633\u062a \u0634\u062f\u0647 \u0627\u0633\u062a \u0631\u0648\u06cc <code>Ubuntu 20.04.1 LTS<\/code>.  \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u0646\u0635\u0628 \u06a9\u0646\u06cc\u062f <code>BeautifulSoup<\/code> \u0645\u0627\u0698\u0648\u0644 \u0628\u0627 \u062a\u0627\u06cc\u067e \u062f\u0633\u062a\u0648\u0631 \u0632\u06cc\u0631 \u062f\u0631 terminal:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-meta\">$<\/span><span class=\"bash\"> pip3 install beautifulsoup4<\/span>\n<\/code><\/pre>\n<p>\u0641\u0627\u06cc\u0644 HTML <code>doc.html<\/code> \u0628\u0627\u06cc\u062f \u0622\u0645\u0627\u062f\u0647 \u0634\u0648\u062f.  \u0627\u06cc\u0646 \u06a9\u0627\u0631 \u0628\u0627 \u0627\u0631\u0633\u0627\u0644 \u0641\u0627\u06cc\u0644 \u0628\u0647 <code>BeautifulSoup<\/code> \u0633\u0627\u0632\u0646\u062f\u0647\u060c \u0628\u06cc\u0627\u06cc\u06cc\u062f \u0627\u0632 \u067e\u0648\u0633\u062a\u0647 \u062a\u0639\u0627\u0645\u0644\u06cc \u067e\u0627\u06cc\u062a\u0648\u0646 \u0628\u0631\u0627\u06cc \u0627\u06cc\u0646 \u06a9\u0627\u0631 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0646\u06cc\u0645 \u062a\u0627 \u0628\u062a\u0648\u0627\u0646\u06cc\u0645 \u0641\u0648\u0631\u0627\u064b print \u0645\u062d\u062a\u0648\u06cc\u0627\u062a \u0642\u0633\u0645\u062a \u062e\u0627\u0635\u06cc \u0627\u0632 a page:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">from<\/span> bs4 <span class=\"hljs-keyword\">import<\/span> BeautifulSoup\n\n<span class=\"hljs-keyword\">with<\/span> <span class=\"hljs-built_in\">open<\/span>(<span class=\"hljs-string\">\"doc.html\"<\/span>) <span class=\"hljs-keyword\">as<\/span> fp:\n    soup = BeautifulSoup(fp, <span class=\"hljs-string\">\"html.parser\"<\/span>)\n<\/code><\/pre>\n<p>\u0627\u06a9\u0646\u0648\u0646 \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u0645 \u0627\u0632 Beautiful Soup \u0628\u0631\u0627\u06cc \u067e\u06cc\u0645\u0627\u06cc\u0634 \u0648\u0628 \u0633\u0627\u06cc\u062a \u062e\u0648\u062f \u0648 \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u062f\u0627\u062f\u0647 \u0647\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0646\u06cc\u0645.<\/p>\n<h3 id=\"navigatingtospecifictags\"><span class=\"ez-toc-section\" id=\"%d9%be%db%8c%d9%85%d8%a7%db%8c%d8%b4_%d8%a8%d9%87_%d8%a8%d8%b1%da%86%d8%b3%d8%a8_%d9%87%d8%a7%db%8c_%d8%ae%d8%a7%d8%b5\"><\/span>\u067e\u06cc\u0645\u0627\u06cc\u0634 \u0628\u0647 \u0628\u0631\u0686\u0633\u0628 \u0647\u0627\u06cc \u062e\u0627\u0635<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u0627\u0632 \u0634\u06cc\u0621 \u0633\u0648\u067e \u0627\u06cc\u062c\u0627\u062f \u0634\u062f\u0647 \u062f\u0631 \u0642\u0633\u0645\u062a \u0642\u0628\u0644\u060c \u062a\u06af \u0639\u0646\u0648\u0627\u0646 \u0631\u0627 \u062f\u0631\u06cc\u0627\u0641\u062a \u0645\u06cc \u06a9\u0646\u06cc\u0645 <code>doc.html<\/code>:<\/p>\n<pre><code class=\"hljs\">soup.head.title   \n<\/code><\/pre>\n<p>\u062f\u0631 \u0627\u06cc\u0646\u062c\u0627 \u0628\u0647 \u062a\u0641\u06a9\u06cc\u06a9 \u0647\u0631 \u0645\u0624\u0644\u0641\u0647 \u0627\u06cc \u06a9\u0647 \u0628\u0631\u0627\u06cc \u0628\u062f\u0633\u062a \u0622\u0648\u0631\u062f\u0646 \u0639\u0646\u0648\u0627\u0646 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0631\u062f\u06cc\u0645\u060c \u0622\u0645\u062f\u0647 \u0627\u0633\u062a:<\/p>\n<p><img decoding=\"async\" src=\"https:\/\/rasanegar.com\/blog\/wp-content\/uploads\/2024\/01\/parsing-html-with-beautifulsoup-in-python-2.jpg\" alt=\"\u067e\u06cc\u0645\u0627\u06cc\u0634 \u0628\u0631\u0686\u0633\u0628 \u0647\u0627\u06cc \u062e\u0627\u0635\" title=\"\"><\/p>\n<p>Beautiful Soup \u0642\u062f\u0631\u062a\u0645\u0646\u062f \u0627\u0633\u062a \u0632\u06cc\u0631\u0627 \u0627\u0634\u06cc\u0627\u0621 \u067e\u0627\u06cc\u062a\u0648\u0646 \u0645\u0627 \u0628\u0627 \u0633\u0627\u062e\u062a\u0627\u0631 \u062a\u0648\u062f\u0631\u062a\u0648\u06cc \u0633\u0646\u062f HTML \u06a9\u0647 \u062f\u0631 \u062d\u0627\u0644 \u062e\u0631\u0627\u0634\u06cc\u062f\u0646 \u0647\u0633\u062a\u06cc\u0645 \u0645\u0637\u0627\u0628\u0642\u062a \u062f\u0627\u0631\u062f.<\/p>\n<p>\u0628\u0631\u0627\u06cc \u062f\u0631\u06cc\u0627\u0641\u062a \u0645\u062a\u0646 \u0627\u0648\u0644 <code>&lt;a&gt;<\/code> \u0628\u0631\u0686\u0633\u0628\u060c \u0627\u06cc\u0646 \u0631\u0627 \u0648\u0627\u0631\u062f \u06a9\u0646\u06cc\u062f:<\/p>\n<pre><code class=\"hljs\">soup.body.a.text  \n<\/code><\/pre>\n<p>\u0628\u0631\u0627\u06cc \u062f\u0631\u06cc\u0627\u0641\u062a \u0639\u0646\u0648\u0627\u0646 \u062f\u0631 \u062a\u06af \u0628\u062f\u0646\u0647 HTML (\u06a9\u0647 \u0628\u0627 \u06a9\u0644\u0627\u0633 &#8220;title&#8221; \u0645\u0634\u062e\u0635 \u0645\u06cc \u0634\u0648\u062f)\u060c \u0645\u0648\u0627\u0631\u062f \u0632\u06cc\u0631 \u0631\u0627 \u062f\u0631 \u062e\u0648\u062f \u062a\u0627\u06cc\u067e \u06a9\u0646\u06cc\u062f. terminal:<\/p>\n<pre><code class=\"hljs\">soup.body.p.b     \n<\/code><\/pre>\n<p>\u0628\u0631\u0627\u06cc \u0627\u0633\u0646\u0627\u062f HTML \u0639\u0645\u06cc\u0642 \u062a\u0648 \u062f\u0631 \u062a\u0648\u060c \u0646\u0627\u0648\u0628\u0631\u06cc \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u0628\u0647 \u0633\u0631\u0639\u062a \u062e\u0633\u062a\u0647 \u06a9\u0646\u0646\u062f\u0647 \u0634\u0648\u062f.  \u062e\u0648\u0634\u0628\u062e\u062a\u0627\u0646\u0647\u060c Beautiful Soup \u062f\u0627\u0631\u0627\u06cc \u06cc\u06a9 \u062a\u0627\u0628\u0639 \u062c\u0633\u062a\u062c\u0648 \u0627\u0633\u062a\u060c \u0628\u0646\u0627\u0628\u0631\u0627\u06cc\u0646 \u0645\u0627 \u0645\u062c\u0628\u0648\u0631 \u0646\u06cc\u0633\u062a\u06cc\u0645 \u0628\u0631\u0627\u06cc \u0628\u0627\u0632\u06cc\u0627\u0628\u06cc \u0639\u0646\u0627\u0635\u0631 HTML \u067e\u06cc\u0645\u0627\u06cc\u0634 \u06a9\u0646\u06cc\u0645.<\/p>\n<h3 id=\"searchingtheelementsoftags\"><span class=\"ez-toc-section\" id=\"%d8%ac%d8%b3%d8%aa%d8%ac%d9%88_%d8%af%d8%b1_%d8%b9%d9%86%d8%a7%d8%b5%d8%b1_%d8%a8%d8%b1%da%86%d8%b3%d8%a8_%d9%87%d8%a7\"><\/span>\u062c\u0633\u062a\u062c\u0648 \u062f\u0631 \u0639\u0646\u0627\u0635\u0631 \u0628\u0631\u0686\u0633\u0628 \u0647\u0627<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u0631\u0627 <code>find_all()<\/code> \u0645\u062a\u062f \u06cc\u06a9 \u062a\u06af HTML \u0631\u0627 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0622\u0631\u06af\u0648\u0645\u0627\u0646 \u0631\u0634\u062a\u0647 \u0627\u06cc \u0645\u06cc \u06af\u06cc\u0631\u062f \u0648 \u0644\u06cc\u0633\u062a \u0639\u0646\u0627\u0635\u0631\u06cc \u0631\u0627 \u06a9\u0647 \u0628\u0627 \u062a\u06af \u0627\u0631\u0627\u0626\u0647 \u0634\u062f\u0647 \u0645\u0637\u0627\u0628\u0642\u062a \u062f\u0627\u0631\u0646\u062f \u0628\u0631\u0645\u06cc \u06af\u0631\u062f\u0627\u0646\u062f.  \u0645\u062b\u0644\u0627\u064b \u0627\u06af\u0631 \u0647\u0645\u0647 \u0631\u0627 \u0628\u062e\u0648\u0627\u0647\u06cc\u0645 <code>a<\/code> \u0628\u0631\u0686\u0633\u0628 \u0647\u0627 \u062f\u0631 <code>doc.html<\/code>:<\/p>\n<pre><code class=\"hljs\">soup.find_all(<span class=\"hljs-string\">\"a\"<\/span>)\n<\/code><\/pre>\n<p>\u0645\u0627 \u0627\u06cc\u0646 \u0644\u06cc\u0633\u062a \u0631\u0627 \u062e\u0648\u0627\u0647\u06cc\u0645 \u062f\u06cc\u062f <code>a<\/code> \u0628\u0631\u0686\u0633\u0628 \u0647\u0627 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u062e\u0631\u0648\u062c\u06cc:<\/p>\n<pre><code class=\"hljs\">(&lt;a class=\"element\" href=\"http:\/\/example.com\/element1\" id=\"link1\"&gt;1&lt;\/a&gt;, &lt;a class=\"element\" href=\"http:\/\/example.com\/element2\" id=\"link2\"&gt;2&lt;\/a&gt;, &lt;a class=\"element\" href=\"http:\/\/example.com\/element3\" id=\"link3\"&gt;3&lt;\/a&gt;)\n<\/code><\/pre>\n<p>\u062f\u0631 \u0627\u06cc\u0646\u062c\u0627 \u0628\u0647 \u062a\u0641\u06a9\u06cc\u06a9 \u0647\u0631 \u0645\u0624\u0644\u0641\u0647 \u0627\u06cc \u06a9\u0647 \u0628\u0631\u0627\u06cc \u062c\u0633\u062a\u062c\u0648\u06cc \u06cc\u06a9 \u0628\u0631\u0686\u0633\u0628 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0631\u062f\u06cc\u0645\u060c \u0622\u0645\u062f\u0647 \u0627\u0633\u062a:<\/p>\n<p><img decoding=\"async\" src=\"https:\/\/rasanegar.com\/blog\/wp-content\/uploads\/2024\/01\/parsing-html-with-beautifulsoup-in-python-3.jpg\" alt=\"\u062c\u0633\u062a\u062c\u0648\u06cc \u0639\u0646\u0627\u0635\u0631 \u0628\u0631\u0686\u0633\u0628 \u0647\u0627\" title=\"\"><\/p>\n<p>\u0647\u0645\u0686\u0646\u06cc\u0646 \u0645\u06cc\u200c\u062a\u0648\u0627\u0646\u06cc\u0645 \u0628\u0631\u0686\u0633\u0628\u200c\u0647\u0627\u06cc \u06cc\u06a9 \u06a9\u0644\u0627\u0633 \u062e\u0627\u0635 \u0631\u0627 \u0628\u0627 \u0627\u0631\u0627\u0626\u0647 \u0622\u0646 \u062c\u0633\u062a\u062c\u0648 \u06a9\u0646\u06cc\u0645 <code>class_<\/code> \u0628\u062d\u062b \u0648 \u062c\u062f\u0644.  \u0645\u0648\u0627\u0631\u062f \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0633\u0648\u067e \u0632\u06cc\u0628\u0627 <code>class_<\/code> \u0632\u06cc\u0631\u0627 <code>class<\/code> \u06cc\u06a9 \u06a9\u0644\u0645\u0647 \u06a9\u0644\u06cc\u062f\u06cc \u0631\u0632\u0631\u0648 \u0634\u062f\u0647 \u062f\u0631 \u067e\u0627\u06cc\u062a\u0648\u0646 \u0627\u0633\u062a.  \u0628\u06cc\u0627\u06cc\u06cc\u062f \u0647\u0645\u0647 \u0631\u0627 \u062c\u0633\u062a\u062c\u0648 \u06a9\u0646\u06cc\u0645 <code>a<\/code> \u0628\u0631\u0686\u0633\u0628 \u0647\u0627\u06cc\u06cc \u06a9\u0647 \u062f\u0627\u0631\u0627\u06cc \u06a9\u0644\u0627\u0633 &#8220;element&#8221; \u0647\u0633\u062a\u0646\u062f:<\/p>\n<pre><code class=\"hljs\">soup.find_all(<span class=\"hljs-string\">\"a\"<\/span>, class_=<span class=\"hljs-string\">\"element\"<\/span>)\n<\/code><\/pre>\n<p>\u0627\u0632 \u0622\u0646\u062c\u0627\u06cc\u06cc \u06a9\u0647 \u0645\u0627 \u0641\u0642\u0637 \u062f\u0648 \u067e\u06cc\u0648\u0646\u062f \u0628\u0627 \u06a9\u0644\u0627\u0633 &#8220;element&#8221; \u062f\u0627\u0631\u06cc\u0645\u060c \u0627\u06cc\u0646 \u062e\u0631\u0648\u062c\u06cc \u0631\u0627 \u062e\u0648\u0627\u0647\u06cc\u062f \u062f\u06cc\u062f:<\/p>\n<pre><code class=\"hljs\">(&lt;a class=\"element\" href=\"http:\/\/example.com\/element1\" id=\"link1\"&gt;1&lt;\/a&gt;, &lt;a class=\"element\" href=\"http:\/\/example.com\/element2\" id=\"link2\"&gt;2&lt;\/a&gt;)\n<\/code><\/pre>\n<p>\u0686\u0647 \u0645\u06cc \u0634\u0648\u062f \u0627\u06af\u0631 \u0628\u062e\u0648\u0627\u0647\u06cc\u0645 \u067e\u06cc\u0648\u0646\u062f\u0647\u0627\u06cc \u062a\u0639\u0628\u06cc\u0647 \u0634\u062f\u0647 \u062f\u0631 \u062f\u0627\u062e\u0644 \u0631\u0627 \u0648\u0627\u06a9\u0634\u06cc \u06a9\u0646\u06cc\u0645 <code>a<\/code> \u0628\u0631\u0686\u0633\u0628 \u0647\u0627\u061f  \u0628\u06cc\u0627\u06cc\u06cc\u062f \u06cc\u06a9 \u067e\u06cc\u0648\u0646\u062f \u0631\u0627 \u0628\u0627\u0632\u06cc\u0627\u0628\u06cc \u06a9\u0646\u06cc\u0645 <code>href<\/code> \u0648\u06cc\u0698\u06af\u06cc \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 <code>find()<\/code> \u06af\u0632\u06cc\u0646\u0647.  \u062f\u0631\u0633\u062a \u0645\u062b\u0644 \u06a9\u0627\u0631 \u0645\u06cc \u06a9\u0646\u062f <code>find_all()<\/code> \u0627\u0645\u0627 \u0628\u0647 \u062c\u0627\u06cc \u0644\u06cc\u0633\u062a\u060c \u0627\u0648\u0644\u06cc\u0646 \u0639\u0646\u0635\u0631 \u062a\u0637\u0628\u06cc\u0642 \u0631\u0627 \u0628\u0631\u0645\u06cc \u06af\u0631\u062f\u0627\u0646\u062f.  \u0627\u06cc\u0646 \u0631\u0627 \u062f\u0631 \u067e\u0648\u0633\u062a\u0647 \u062e\u0648\u062f \u062a\u0627\u06cc\u067e \u06a9\u0646\u06cc\u062f:<\/p>\n<pre><code class=\"hljs\">soup.find(<span class=\"hljs-string\">\"a\"<\/span>, href=<span class=\"hljs-literal\">True<\/span>)(<span class=\"hljs-string\">\"href\"<\/span>) \n<\/code><\/pre>\n<p>\u0631\u0627 <code>find()<\/code> \u0648 <code>find_all()<\/code> \u062a\u0648\u0627\u0628\u0639 \u0646\u06cc\u0632 \u0628\u0647 \u062c\u0627\u06cc \u0631\u0634\u062a\u0647\u060c \u06cc\u06a9 \u0639\u0628\u0627\u0631\u062a \u0645\u0646\u0638\u0645 \u0631\u0627 \u0645\u06cc \u067e\u0630\u06cc\u0631\u0646\u062f.  \u062f\u0631 \u067e\u0634\u062a \u0635\u062d\u0646\u0647\u060c \u0645\u062a\u0646 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0639\u0628\u0627\u0631\u062a \u0645\u0646\u0638\u0645 \u06a9\u0627\u0645\u067e\u0627\u06cc\u0644 \u0634\u062f\u0647 \u0641\u06cc\u0644\u062a\u0631 \u0645\u06cc \u0634\u0648\u062f <code>search()<\/code> \u0631\u0648\u0634.  \u0645\u062b\u0644\u0627:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">import<\/span> re\n\n<span class=\"hljs-keyword\">for<\/span> tag <span class=\"hljs-keyword\">in<\/span> soup.find_all(re.<span class=\"hljs-built_in\">compile<\/span>(<span class=\"hljs-string\">\"^b\"<\/span>)):\n    <span class=\"hljs-built_in\">print<\/span>(tag)\n<\/code><\/pre>\n<p>\u0644\u06cc\u0633\u062a \u067e\u0633 \u0627\u0632 \u062a\u06a9\u0631\u0627\u0631\u060c \u0628\u0631\u0686\u0633\u0628 \u0647\u0627\u06cc\u06cc \u0631\u0627 \u06a9\u0647 \u0628\u0627 \u06a9\u0627\u0631\u0627\u06a9\u062a\u0631 \u0634\u0631\u0648\u0639 \u0645\u06cc \u0634\u0648\u0646\u062f \u0648\u0627\u06a9\u0634\u06cc \u0645\u06cc \u06a9\u0646\u062f <code>b<\/code> \u06a9\u0647 \u0634\u0627\u0645\u0644 <code>&lt;body&gt;<\/code> \u0648 <code>&lt;b&gt;<\/code>:<\/p>\n<pre><code class=\"hljs\">&lt;body&gt;\n &lt;p class=\"title\"&gt;&lt;b&gt;Body's title&lt;\/b&gt;&lt;\/p&gt;\n &lt;p class=\"story\"&gt;line begins\n       &lt;a class=\"element\" href=\"http:\/\/example.com\/element1\" id=\"link1\"&gt;1&lt;\/a&gt;\n &lt;a class=\"element\" href=\"http:\/\/example.com\/element2\" id=\"link2\"&gt;2&lt;\/a&gt;\n &lt;a class=\"element\" href=\"http:\/\/example.com\/element3\" id=\"link3\"&gt;3&lt;\/a&gt;\n &lt;p&gt; line ends&lt;\/p&gt;\n &lt;\/p&gt;&lt;\/body&gt;\n &lt;b&gt;Body's title&lt;\/b&gt;\n<\/code><\/pre>\n<p>\u0645\u0627 \u0645\u062d\u0628\u0648\u0628 \u062a\u0631\u06cc\u0646 \u0631\u0648\u0634 \u0647\u0627\u06cc \u062f\u0631\u06cc\u0627\u0641\u062a \u0628\u0631\u0686\u0633\u0628 \u0647\u0627 \u0648 \u0648\u06cc\u0698\u06af\u06cc \u0647\u0627\u06cc \u0622\u0646\u0647\u0627 \u0631\u0627 \u067e\u0648\u0634\u0634 \u062f\u0627\u062f\u0647 \u0627\u06cc\u0645.  \u06af\u0627\u0647\u06cc \u0627\u0648\u0642\u0627\u062a\u060c \u0628\u0647 \u062e\u0635\u0648\u0635 \u0628\u0631\u0627\u06cc \u0635\u0641\u062d\u0627\u062a \u0648\u0628 \u06a9\u0645\u062a\u0631 \u067e\u0648\u06cc\u0627\u060c \u0641\u0642\u0637 \u0645\u062a\u0646 \u0631\u0627 \u0627\u0632 \u0622\u0646 \u0645\u06cc \u062e\u0648\u0627\u0647\u06cc\u0645.  \u0628\u06cc\u0627\u06cc\u06cc\u062f \u0628\u0628\u06cc\u0646\u06cc\u0645 \u0686\u06af\u0648\u0646\u0647 \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u0645 \u0622\u0646 \u0631\u0627 \u0628\u062f\u0633\u062a \u0622\u0648\u0631\u06cc\u0645!<\/p>\n<h3 id=\"gettingthewholetext\"><span class=\"ez-toc-section\" id=\"%d8%af%d8%b1%db%8c%d8%a7%d9%81%d8%aa_%da%a9%d9%84_%d9%85%d8%aa%d9%86\"><\/span>\u062f\u0631\u06cc\u0627\u0641\u062a \u06a9\u0644 \u0645\u062a\u0646<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u0631\u0627 <code>get_text()<\/code> \u062a\u0627\u0628\u0639 \u062a\u0645\u0627\u0645 \u0645\u062a\u0646 \u0631\u0627 \u0627\u0632 \u0633\u0646\u062f HTML \u0628\u0627\u0632\u06cc\u0627\u0628\u06cc \u0645\u06cc \u06a9\u0646\u062f.  \u0628\u06cc\u0627\u06cc\u06cc\u062f \u062a\u0645\u0627\u0645 \u0645\u062a\u0646 \u0633\u0646\u062f HTML \u0631\u0627 \u062f\u0631\u06cc\u0627\u0641\u062a \u06a9\u0646\u06cc\u0645:<\/p>\n<pre><code class=\"hljs\">soup.get_text()\n<\/code><\/pre>\n<p>\u062e\u0631\u0648\u062c\u06cc \u0634\u0645\u0627 \u0628\u0627\u06cc\u062f \u0628\u0647 \u0627\u06cc\u0646 \u0635\u0648\u0631\u062a \u0628\u0627\u0634\u062f:<\/p>\n<pre><code class=\"hljs\">Head's title\n\n\nBody's title\nline begins\n      1\n2\n3\n line ends\n<\/code><\/pre>\n<p>\u06af\u0627\u0647\u06cc \u0627\u0648\u0642\u0627\u062a \u06a9\u0627\u0631\u0627\u06a9\u062a\u0631\u0647\u0627\u06cc \u062e\u0637 \u062c\u062f\u06cc\u062f \u0686\u0627\u067e \u0645\u06cc \u0634\u0648\u0646\u062f\u060c \u0628\u0646\u0627\u0628\u0631\u0627\u06cc\u0646 \u062e\u0631\u0648\u062c\u06cc \u0634\u0645\u0627 \u0645\u0645\u06a9\u0646 \u0627\u0633\u062a \u0628\u0647 \u0627\u06cc\u0646 \u0634\u06a9\u0644 \u0628\u0627\u0634\u062f:<\/p>\n<pre><code class=\"hljs\">\"\\n\\nHead's title\\n\\n\\nBody's title\\nline begins\\n    1\\n2\\n3\\n line ends\\n\\n\"\n<\/code><\/pre>\n<p>\u0627\u06a9\u0646\u0648\u0646 \u06a9\u0647 \u0627\u062d\u0633\u0627\u0633 \u0645\u06cc \u06a9\u0646\u06cc\u0645 \u0686\u06af\u0648\u0646\u0647 \u0627\u0632 \u0633\u0648\u067e \u0632\u06cc\u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0646\u06cc\u0645\u060c \u0628\u06cc\u0627\u06cc\u06cc\u062f \u06cc\u06a9 \u0648\u0628 \u0633\u0627\u06cc\u062a \u0631\u0627 \u062e\u0631\u0627\u0634 \u062f\u0647\u06cc\u0645!<\/p>\n<h2 id=\"beautifulsoupinactionscrapingabooklist\"><span class=\"ez-toc-section\" id=\"%d8%b3%d9%88%d9%be_%d8%b2%db%8c%d8%a8%d8%a7_%d8%af%d8%b1_%d8%b9%d9%85%d9%84_%e2%80%93_%d8%aa%d9%87%db%8c%d9%87_%d9%81%d9%87%d8%b1%d8%b3%d8%aa_%da%a9%d8%aa%d8%a7%d8%a8\"><\/span>\u0633\u0648\u067e \u0632\u06cc\u0628\u0627 \u062f\u0631 \u0639\u0645\u0644 &#8211; \u062a\u0647\u06cc\u0647 \u0641\u0647\u0631\u0633\u062a \u06a9\u062a\u0627\u0628<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>\u0627\u06a9\u0646\u0648\u0646 \u06a9\u0647 \u0628\u0631 \u0627\u062c\u0632\u0627\u06cc \u0633\u0648\u067e \u0632\u06cc\u0628\u0627 \u062a\u0633\u0644\u0637 \u062f\u0627\u0631\u06cc\u0645\u060c \u0648\u0642\u062a \u0622\u0646 \u0627\u0633\u062a \u06a9\u0647 \u0627\u0632 \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u062e\u0648\u062f \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0646\u06cc\u0645.  \u0628\u06cc\u0627\u06cc\u06cc\u062f \u06cc\u06a9 \u0627\u0633\u06a9\u0631\u0627\u067e\u0631 \u0628\u0631\u0627\u06cc \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u062f\u0627\u062f\u0647 \u0647\u0627 \u0628\u0633\u0627\u0632\u06cc\u0645 <a href=\"https:\/\/books.toscrape.com\/\" rel=\"nofollow noopener\" target=\"_blank\" class=\"broken_link\">https:\/\/books.toscrape.com\/<\/a> \u0648 \u0622\u0646 \u0631\u0627 \u062f\u0631 \u06cc\u06a9 \u0641\u0627\u06cc\u0644 CSV \u0630\u062e\u06cc\u0631\u0647 \u06a9\u0646\u06cc\u062f.  \u0627\u06cc\u0646 \u0633\u0627\u06cc\u062a \u062d\u0627\u0648\u06cc \u062f\u0627\u062f\u0647\u200c\u0647\u0627\u06cc \u062a\u0635\u0627\u062f\u0641\u06cc \u062f\u0631\u0628\u0627\u0631\u0647 \u06a9\u062a\u0627\u0628\u200c\u0647\u0627 \u0627\u0633\u062a \u0648 \u0641\u0636\u0627\u06cc\u06cc \u0639\u0627\u0644\u06cc \u0628\u0631\u0627\u06cc \u0622\u0632\u0645\u0627\u06cc\u0634 \u062a\u06a9\u0646\u06cc\u06a9\u200c\u0647\u0627\u06cc \u062e\u0631\u0627\u0634 \u062f\u0627\u062f\u0646 \u0648\u0628 \u0634\u0645\u0627 \u0627\u0633\u062a.<\/p>\n<p>\u0627\u0628\u062a\u062f\u0627 \u06cc\u06a9 \u0641\u0627\u06cc\u0644 \u062c\u062f\u06cc\u062f \u0628\u0647 \u0646\u0627\u0645 \u0627\u06cc\u062c\u0627\u062f \u06a9\u0646\u06cc\u062f <code>scraper.py<\/code>.  \u0627\u062c\u0627\u0632\u0647 \u062f\u0647\u06cc\u062f import \u062a\u0645\u0627\u0645 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0647\u0627\u06cc\u06cc \u06a9\u0647 \u0628\u0631\u0627\u06cc \u0627\u06cc\u0646 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0646\u06cc\u0627\u0632 \u062f\u0627\u0631\u06cc\u0645:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">import<\/span> requests\n<span class=\"hljs-keyword\">import<\/span> time\n<span class=\"hljs-keyword\">import<\/span> csv\n<span class=\"hljs-keyword\">import<\/span> re\n<span class=\"hljs-keyword\">from<\/span> bs4 <span class=\"hljs-keyword\">import<\/span> BeautifulSoup\n<\/code><\/pre>\n<p>\u062f\u0631 \u0645\u0627\u0698\u0648\u0644 \u0647\u0627\u06cc \u0630\u06a9\u0631 \u0634\u062f\u0647 \u062f\u0631 \u0628\u0627\u0644\u0627:<\/p>\n<ul>\n<li><code>requests<\/code>  &#8211; \u062f\u0631\u062e\u0648\u0627\u0633\u062a URL \u0631\u0627 \u0627\u0646\u062c\u0627\u0645 \u0645\u06cc \u062f\u0647\u062f \u0648 HTML \u0648\u0628 \u0633\u0627\u06cc\u062a \u0631\u0627 \u0648\u0627\u06a9\u0634\u06cc \u0645\u06cc \u06a9\u0646\u062f<\/li>\n<li><code>time<\/code>  &#8211; \u062a\u0639\u062f\u0627\u062f \u062f\u0641\u0639\u0627\u062a \u062e\u0631\u0627\u0634\u06cc\u062f\u0646 \u0631\u0627 \u0645\u062d\u062f\u0648\u062f \u0645\u06cc \u06a9\u0646\u062f page \u0641\u0648\u0631\u0627<\/li>\n<li><code>csv<\/code>  &#8211; \u0628\u0647 \u0645\u0627 \u06a9\u0645\u06a9 \u0645\u06cc \u06a9\u0646\u062f export \u062f\u0627\u062f\u0647 \u0647\u0627\u06cc \u062e\u0631\u0627\u0634\u06cc\u062f\u0647 \u0634\u062f\u0647 \u0645\u0627 \u062f\u0631 \u06cc\u06a9 \u0641\u0627\u06cc\u0644 CSV<\/li>\n<li><code>re<\/code>  &#8211; \u0628\u0647 \u0645\u0627 \u0627\u0645\u06a9\u0627\u0646 \u0645\u06cc \u062f\u0647\u062f \u0639\u0628\u0627\u0631\u0627\u062a \u0645\u0646\u0638\u0645\u06cc \u0631\u0627 \u0628\u0646\u0648\u06cc\u0633\u06cc\u0645 \u06a9\u0647 \u0628\u0631\u0627\u06cc \u0627\u0646\u062a\u062e\u0627\u0628 \u0645\u062a\u0646 \u0628\u0631 \u0627\u0633\u0627\u0633 \u0645\u0641\u06cc\u062f \u0628\u0627\u0634\u062f \u0631\u0648\u06cc \u0627\u0644\u06af\u0648\u06cc \u0622\u0646<\/li>\n<li><code>bs4<\/code>  &#8211; \u0648\u0627\u0642\u0639\u0627\u064b \u0645\u0627\u0644 \u0634\u0645\u0627\u060c \u0645\u0627\u0698\u0648\u0644 \u062e\u0631\u0627\u0634 \u0628\u0631\u0627\u06cc \u062a\u062c\u0632\u06cc\u0647 HTML<\/li>\n<\/ul>\n<p>\u0634\u0645\u0627 \u0628\u0627\u06cc\u062f \u062f\u0627\u0634\u062a\u0647 \u0628\u0627\u0634\u06cc\u062f <code>bs4<\/code> \u0642\u0628\u0644\u0627 \u0646\u0635\u0628 \u0634\u062f\u0647 \u0627\u0633\u062a\u060c \u0648 <code>time<\/code>\u060c <code>csv<\/code>\u060c \u0648 <code>re<\/code> \u0628\u0633\u062a\u0647 \u0647\u0627\u06cc \u062f\u0627\u062e\u0644\u06cc \u062f\u0631 \u067e\u0627\u06cc\u062a\u0648\u0646 \u0647\u0633\u062a\u0646\u062f.  \u0634\u0645\u0627 \u0628\u0627\u06cc\u062f \u0646\u0635\u0628 \u06a9\u0646\u06cc\u062f <code>requests<\/code> \u0645\u0627\u0698\u0648\u0644 \u0628\u0647 \u0637\u0648\u0631 \u0645\u0633\u062a\u0642\u06cc\u0645 \u0645\u0627\u0646\u0646\u062f \u0627\u06cc\u0646:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-meta\">$<\/span><span class=\"bash\"> pip3 install requests<\/span>\n<\/code><\/pre>\n<p>\u0642\u0628\u0644 \u0627\u0632 \u0634\u0631\u0648\u0639\u060c \u0628\u0627\u06cc\u062f \u0628\u062f\u0627\u0646\u06cc\u062f \u0633\u0627\u062e\u062a\u0627\u0631 HTML \u0635\u0641\u062d\u0647 \u0648\u0628 \u0686\u06af\u0648\u0646\u0647 \u0627\u0633\u062a.  \u062f\u0631 \u0645\u0631\u0648\u0631\u06af\u0631 \u0634\u0645\u0627\u060c \u0628\u06cc\u0627\u06cc\u06cc\u062f \u0628\u0647 <a href=\"http:\/\/books.toscrape.com\/catalogue\/page-1.html\" rel=\"nofollow noopener\" target=\"_blank\" class=\"broken_link\">http:\/\/books.toscrape.com\/catalogue\/page-1.html<\/a>.  \u0633\u067e\u0633 \u0631\u0627\u0633\u062a \u06a9\u0644\u06cc\u06a9 \u06a9\u0646\u06cc\u062f \u0631\u0648\u06cc \u0627\u062c\u0632\u0627\u06cc \u0648\u0628 page \u062e\u0631\u0627\u0634\u06cc\u062f\u0647 \u0634\u0648\u062f \u0648 \u06a9\u0644\u06cc\u06a9 \u06a9\u0646\u06cc\u062f \u0631\u0648\u06cc \u0631\u0627 <strong>\u0628\u0627\u0632\u0631\u0633\u06cc<\/strong> \u0628\u0631\u0627\u06cc \u062f\u0631\u06a9 \u0633\u0644\u0633\u0644\u0647 \u0645\u0631\u0627\u062a\u0628 \u062a\u06af \u0647\u0627 \u0647\u0645\u0627\u0646\u0637\u0648\u0631 \u06a9\u0647 \u062f\u0631 \u0632\u06cc\u0631 \u0646\u0634\u0627\u0646 \u062f\u0627\u062f\u0647 \u0634\u062f\u0647 \u0627\u0633\u062a \u0631\u0627 \u0641\u0634\u0627\u0631 \u062f\u0647\u06cc\u062f.<\/p>\n<p>\u0627\u06cc\u0646 HTML \u0632\u06cc\u0631\u0628\u0646\u0627\u06cc\u06cc \u0631\u0627 \u0628\u0631\u0627\u06cc \u0622\u0646\u0686\u0647 \u06a9\u0647 \u062f\u0631 \u062d\u0627\u0644 \u0628\u0631\u0631\u0633\u06cc \u0647\u0633\u062a\u06cc\u062f \u0628\u0647 \u0634\u0645\u0627 \u0646\u0634\u0627\u0646 \u0645\u06cc \u062f\u0647\u062f.  \u062a\u0635\u0648\u06cc\u0631 \u0632\u06cc\u0631 \u0627\u06cc\u0646 \u0645\u0631\u0627\u062d\u0644 \u0631\u0627 \u0646\u0634\u0627\u0646 \u0645\u06cc \u062f\u0647\u062f:<\/p>\n<p><img decoding=\"async\" src=\"https:\/\/rasanegar.com\/blog\/wp-content\/uploads\/2024\/01\/parsing-html-with-beautifulsoup-in-python-4.gif\" alt=\"\u0622\u0634\u0646\u0627\u06cc\u06cc \u0628\u0627 \u062a\u06af \u0647\u0627\u06cc HTML\" title=\"\"><\/p>\n<p>\u0627\u0632 \u0628\u0631\u0631\u0633\u06cc HTML\u060c \u0631\u0648\u0634 \u062f\u0633\u062a\u0631\u0633\u06cc \u0628\u0647 URL \u06a9\u062a\u0627\u0628\u060c \u062a\u0635\u0648\u06cc\u0631 \u062c\u0644\u062f\u060c \u0639\u0646\u0648\u0627\u0646\u060c \u0631\u062a\u0628\u0647 \u0628\u0646\u062f\u06cc\u060c \u0642\u06cc\u0645\u062a \u0648 \u0641\u06cc\u0644\u062f\u0647\u0627\u06cc \u0628\u06cc\u0634\u062a\u0631 \u0627\u0632 HTML \u0631\u0627 \u06cc\u0627\u062f \u0645\u06cc \u06af\u06cc\u0631\u06cc\u0645.  \u0628\u06cc\u0627\u06cc\u06cc\u062f \u062a\u0627\u0628\u0639\u06cc \u0628\u0646\u0648\u06cc\u0633\u06cc\u0645 \u06a9\u0647 \u06cc\u06a9 \u0622\u06cc\u062a\u0645 \u06a9\u062a\u0627\u0628 \u0631\u0627 \u062e\u0631\u0627\u0634 \u0645\u06cc \u062f\u0647\u062f \u0648 \u062f\u0627\u062f\u0647 \u0647\u0627\u06cc \u0622\u0646 \u0631\u0627 \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u0645\u06cc \u06a9\u0646\u062f:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-function\"><span class=\"hljs-keyword\">def<\/span> <span class=\"hljs-title\">scrape<\/span>(<span class=\"hljs-params\">source_url, soup<\/span>):<\/span>  \n    \n    books = soup.find_all(<span class=\"hljs-string\">\"article\"<\/span>, class_=<span class=\"hljs-string\">\"product_pod\"<\/span>)\n\n    \n    <span class=\"hljs-keyword\">for<\/span> each_book <span class=\"hljs-keyword\">in<\/span> books:\n        info_url = source_url+<span class=\"hljs-string\">\"\/\"<\/span>+each_book.h3.find(<span class=\"hljs-string\">\"a\"<\/span>)(<span class=\"hljs-string\">\"href\"<\/span>)\n        cover_url = source_url+<span class=\"hljs-string\">\"\/catalogue\"<\/span> + \\\n            each_book.a.img(<span class=\"hljs-string\">\"src\"<\/span>).replace(<span class=\"hljs-string\">\"..\"<\/span>, <span class=\"hljs-string\">\"\"<\/span>)\n\n        title = each_book.h3.find(<span class=\"hljs-string\">\"a\"<\/span>)(<span class=\"hljs-string\">\"title\"<\/span>)\n        rating = each_book.find(<span class=\"hljs-string\">\"p\"<\/span>, class_=<span class=\"hljs-string\">\"star-rating\"<\/span>)(<span class=\"hljs-string\">\"class\"<\/span>)(<span class=\"hljs-number\">1<\/span>)\n        \n        price = each_book.find(<span class=\"hljs-string\">\"p\"<\/span>, class_=<span class=\"hljs-string\">\"price_color\"<\/span>).text.strip().encode(\n            <span class=\"hljs-string\">\"ascii\"<\/span>, <span class=\"hljs-string\">\"ignore\"<\/span>).decode(<span class=\"hljs-string\">\"ascii\"<\/span>)\n        availability = each_book.find(\n            <span class=\"hljs-string\">\"p\"<\/span>, class_=<span class=\"hljs-string\">\"instock availability\"<\/span>).text.strip()\n\n        \n        write_to_csv((info_url, cover_url, title, rating, price, availability))\n<\/code><\/pre>\n<p>\u0622\u062e\u0631\u06cc\u0646 \u062e\u0637 \u0627\u0632 \u0642\u0637\u0639\u0647 \u0628\u0627\u0644\u0627 \u0628\u0647 \u062a\u0627\u0628\u0639\u06cc \u0627\u0634\u0627\u0631\u0647 \u0645\u06cc \u06a9\u0646\u062f \u06a9\u0647 \u0644\u06cc\u0633\u062a \u0631\u0634\u062a\u0647 \u0647\u0627\u06cc \u062e\u0631\u0627\u0634\u06cc\u062f\u0647 \u0634\u062f\u0647 \u0631\u0627 \u062f\u0631 \u06cc\u06a9 \u0641\u0627\u06cc\u0644 CSV \u0628\u0646\u0648\u06cc\u0633\u062f.  \u0627\u06a9\u0646\u0648\u0646 \u0622\u0646 \u062a\u0627\u0628\u0639 \u0631\u0627 \u0627\u0636\u0627\u0641\u0647 \u0645\u06cc \u06a9\u0646\u06cc\u0645:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-function\"><span class=\"hljs-keyword\">def<\/span> <span class=\"hljs-title\">write_to_csv<\/span>(<span class=\"hljs-params\">list_input<\/span>):<\/span>\n    \n    <span class=\"hljs-keyword\">try<\/span>:\n        <span class=\"hljs-keyword\">with<\/span> <span class=\"hljs-built_in\">open<\/span>(<span class=\"hljs-string\">\"allBooks.csv\"<\/span>, <span class=\"hljs-string\">\"a\"<\/span>) <span class=\"hljs-keyword\">as<\/span> fopen:  \n            csv_writer = csv.writer(fopen)\n            csv_writer.writerow(list_input)\n    <span class=\"hljs-keyword\">except<\/span>:\n        <span class=\"hljs-keyword\">return<\/span> <span class=\"hljs-literal\">False<\/span>\n<\/code><\/pre>\n<p>\u0647\u0645\u0627\u0646\u0637\u0648\u0631 \u06a9\u0647 \u0645\u0627 \u062a\u0627\u0628\u0639\u06cc \u062f\u0627\u0631\u06cc\u0645 \u06a9\u0647 \u0645\u06cc \u062a\u0648\u0627\u0646\u062f a \u0631\u0627 \u062e\u0631\u0627\u0634 \u062f\u0647\u062f page \u0648 export \u0628\u0647 CSV\u060c \u0645\u0627 \u062a\u0627\u0628\u0639 \u062f\u06cc\u06af\u0631\u06cc \u0645\u06cc \u062e\u0648\u0627\u0647\u06cc\u0645 \u06a9\u0647 \u062f\u0631 \u0648\u0628 \u0633\u0627\u06cc\u062a \u0635\u0641\u062d\u0647 \u0628\u0646\u062f\u06cc \u0634\u062f\u0647 \u0645\u06cc \u062e\u0632\u062f \u0648 \u062f\u0627\u062f\u0647 \u0647\u0627\u06cc \u06a9\u062a\u0627\u0628 \u0631\u0627 \u062c\u0645\u0639 \u0622\u0648\u0631\u06cc \u0645\u06cc \u06a9\u0646\u062f \u0631\u0648\u06cc \u0647\u0631 \u06cc\u06a9 page.<\/p>\n<p>\u0628\u0631\u0627\u06cc \u0627\u0646\u062c\u0627\u0645 \u0627\u06cc\u0646 \u06a9\u0627\u0631\u060c \u0628\u06cc\u0627\u06cc\u06cc\u062f \u0628\u0647 \u0622\u062f\u0631\u0633 \u0627\u06cc\u0646\u062a\u0631\u0646\u062a\u06cc \u06a9\u0647 \u0627\u06cc\u0646 \u0627\u0633\u06a9\u0631\u0627\u067e\u0631 \u0631\u0627 \u0628\u0631\u0627\u06cc \u0622\u0646 \u0645\u06cc \u0646\u0648\u06cc\u0633\u06cc\u0645 \u0646\u06af\u0627\u0647 \u06a9\u0646\u06cc\u0645:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-string\">\"http:\/\/books.toscrape.com\/catalogue\/page-1.html\"<\/span>\n<\/code><\/pre>\n<p>\u062a\u0646\u0647\u0627 \u0639\u0646\u0635\u0631 \u0645\u062a\u0641\u0627\u0648\u062a \u062f\u0631 URL \u0627\u0633\u062a page \u0639\u062f\u062f.  \u0645\u0627 \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u0645 URL \u0631\u0627 \u0628\u0647 \u0635\u0648\u0631\u062a \u067e\u0648\u06cc\u0627 \u0642\u0627\u0644\u0628 \u0628\u0646\u062f\u06cc \u06a9\u0646\u06cc\u0645 \u062a\u0627 \u0628\u0647 a \u062a\u0628\u062f\u06cc\u0644 \u0634\u0648\u062f <em>\u0646\u0634\u0627\u0646\u06cc \u0648\u0628 \u0627\u0648\u0644\u06cc\u0647<\/em>:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-string\">\"http:\/\/books.toscrape.com\/catalogue\/page-{}.html\"<\/span>.<span class=\"hljs-built_in\">format<\/span>(<span class=\"hljs-built_in\">str<\/span>(page_number))\n<\/code><\/pre>\n<p>\u0627\u06cc\u0646 \u0631\u0634\u062a\u0647 URL \u0631\u0627 \u0628\u0627 page \u0634\u0645\u0627\u0631\u0647 \u0631\u0627 \u0645\u06cc \u062a\u0648\u0627\u0646 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0631\u0648\u0634 \u0648\u0627\u06a9\u0634\u06cc \u06a9\u0631\u062f <code>requests.get()<\/code>.  \u0633\u067e\u0633 \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u0645 \u06cc\u06a9 \u062c\u062f\u06cc\u062f \u0627\u06cc\u062c\u0627\u062f \u06a9\u0646\u06cc\u0645 <code>BeautifulSoup<\/code> \u0647\u062f\u0641 &#8211; \u0634\u06cc.  \u0647\u0631 \u0628\u0627\u0631 \u06a9\u0647 \u0645\u0627 \u0634\u06cc\u0621 \u0633\u0648\u067e \u0631\u0627 \u062f\u0631\u06cc\u0627\u0641\u062a \u0645\u06cc \u06a9\u0646\u06cc\u0645\u060c \u0648\u062c\u0648\u062f \u062f\u06a9\u0645\u0647 &#8220;\u0628\u0639\u062f\u06cc&#8221; \u0628\u0631\u0631\u0633\u06cc \u0645\u06cc \u0634\u0648\u062f \u062a\u0627 \u0628\u062a\u0648\u0627\u0646\u06cc\u0645 \u062f\u0631 \u0622\u062e\u0631 \u062a\u0648\u0642\u0641 \u06a9\u0646\u06cc\u0645. page.  \u0645\u0627 \u067e\u06cc\u06af\u06cc\u0631\u06cc \u06cc\u06a9 \u0634\u0645\u0627\u0631\u0646\u062f\u0647 \u0628\u0631\u0627\u06cc page \u0639\u062f\u062f\u06cc \u06a9\u0647 \u067e\u0633 \u0627\u0632 \u062e\u0631\u0627\u0634 \u062f\u0627\u062f\u0646 \u0645\u0648\u0641\u0642\u06cc\u062a \u0622\u0645\u06cc\u0632 a \u0628\u0647 \u0645\u06cc\u0632\u0627\u0646 1 \u0627\u0641\u0632\u0627\u06cc\u0634 \u0645\u06cc \u06cc\u0627\u0628\u062f page.<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-function\"><span class=\"hljs-keyword\">def<\/span> <span class=\"hljs-title\">browse_and_scrape<\/span>(<span class=\"hljs-params\">seed_url, page_number=<span class=\"hljs-number\">1<\/span><\/span>):<\/span>\n    \n    url_pat = re.<span class=\"hljs-built_in\">compile<\/span>(<span class=\"hljs-string\">r\"(http:\/\/.*\\.com)\"<\/span>)\n    source_url = url_pat.search(seed_url).group(<span class=\"hljs-number\">0<\/span>)\n\n   \n    formatted_url = seed_url.<span class=\"hljs-built_in\">format<\/span>(<span class=\"hljs-built_in\">str<\/span>(page_number))\n\n    <span class=\"hljs-keyword\">try<\/span>:\n        html_text = requests.get(formatted_url).text\n        \n        soup = BeautifulSoup(html_text, <span class=\"hljs-string\">\"html.parser\"<\/span>)\n        <span class=\"hljs-built_in\">print<\/span>(<span class=\"hljs-string\">f\"Now Scraping - <span class=\"hljs-subst\">{formatted_url}<\/span>\"<\/span>)\n\n        \n        <span class=\"hljs-keyword\">if<\/span> soup.find(<span class=\"hljs-string\">\"li\"<\/span>, class_=<span class=\"hljs-string\">\"next\"<\/span>) != <span class=\"hljs-literal\">None<\/span>:\n            scrape(source_url, soup)     \n            \n            time.sleep(<span class=\"hljs-number\">3<\/span>)\n            page_number += <span class=\"hljs-number\">1<\/span>\n            \n            browse_and_scrape(seed_url, page_number)\n        <span class=\"hljs-keyword\">else<\/span>:\n            scrape(source_url, soup)     \n            <span class=\"hljs-keyword\">return<\/span> <span class=\"hljs-literal\">True<\/span>\n        <span class=\"hljs-keyword\">return<\/span> <span class=\"hljs-literal\">True<\/span>\n    <span class=\"hljs-keyword\">except<\/span> Exception <span class=\"hljs-keyword\">as<\/span> e:\n        <span class=\"hljs-keyword\">return<\/span> e\n<\/code><\/pre>\n<p>\u062a\u0627\u0628\u0639 \u0628\u0627\u0644\u0627\u060c <code>browse_and_scrape()<\/code>\u060c \u0628\u0647 \u0635\u0648\u0631\u062a \u0628\u0627\u0632\u06af\u0634\u062a\u06cc \u062a\u0627 \u062a\u0627\u0628\u0639 \u0641\u0631\u0627\u062e\u0648\u0627\u0646\u06cc \u0645\u06cc \u0634\u0648\u062f <code>soup.find(\"li\",class_=\"next\")<\/code> \u0628\u0631\u0645\u06cc \u06af\u0631\u062f\u0627\u0646\u062f <code>None<\/code>.  \u062f\u0631 \u0627\u06cc\u0646 \u0645\u0631\u062d\u0644\u0647\u060c \u06a9\u062f \u0642\u0633\u0645\u062a \u0628\u0627\u0642\u06cc \u0645\u0627\u0646\u062f\u0647 \u0627\u0632 \u0635\u0641\u062d\u0647 \u0648\u0628 \u0631\u0627 \u062e\u0631\u0627\u0634 \u0645\u06cc \u062f\u0647\u062f \u0648 \u0627\u0632 \u0622\u0646 \u062e\u0627\u0631\u062c \u0645\u06cc \u0634\u0648\u062f.<\/p>\n<p>\u0628\u0631\u0627\u06cc \u0642\u0637\u0639\u0647 \u0646\u0647\u0627\u06cc\u06cc \u0628\u0647 \u067e\u0627\u0632\u0644\u060c \u062c\u0631\u06cc\u0627\u0646 \u062e\u0631\u0627\u0634 \u0631\u0627 \u0622\u063a\u0627\u0632 \u0645\u06cc \u06a9\u0646\u06cc\u0645.  \u0631\u0627 \u062a\u0639\u0631\u06cc\u0641 \u0645\u06cc \u06a9\u0646\u06cc\u0645 <code>seed_url<\/code> \u0648 \u062a\u0645\u0627\u0633 \u0628\u06af\u06cc\u0631\u06cc\u062f <code>browse_and_scrape()<\/code> \u0628\u0631\u0627\u06cc \u0628\u062f\u0633\u062a \u0622\u0648\u0631\u062f\u0646 \u062f\u0627\u062f\u0647 \u0647\u0627  \u0627\u06cc\u0646 \u06a9\u0627\u0631 \u062f\u0631 \u0632\u06cc\u0631 \u0627\u0646\u062c\u0627\u0645 \u0645\u06cc \u0634\u0648\u062f <code>if __name__ == \"__main__\"<\/code> \u0645\u0633\u062f\u0648\u062f \u06a9\u0631\u062f\u0646:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">if<\/span> __name__ == <span class=\"hljs-string\">\"__main__\"<\/span>:\n    seed_url = <span class=\"hljs-string\">\"http:\/\/books.toscrape.com\/catalogue\/page-{}.html\"<\/span>\n    <span class=\"hljs-built_in\">print<\/span>(<span class=\"hljs-string\">\"Web scraping has begun\"<\/span>)\n    result = browse_and_scrape(seed_url)\n    <span class=\"hljs-keyword\">if<\/span> result == <span class=\"hljs-literal\">True<\/span>:\n        <span class=\"hljs-built_in\">print<\/span>(<span class=\"hljs-string\">\"Web scraping is now complete!\"<\/span>)\n    <span class=\"hljs-keyword\">else<\/span>:\n        <span class=\"hljs-built_in\">print<\/span>(<span class=\"hljs-string\">f\"Oops, That doesn't seem right!!! - <span class=\"hljs-subst\">{result}<\/span>\"<\/span>)\n<\/code><\/pre>\n<p>\u0627\u06af\u0631 \u0645\u06cc \u062e\u0648\u0627\u0647\u06cc\u062f \u062f\u0631 \u0645\u0648\u0631\u062f \u0622\u0646 \u0628\u06cc\u0634\u062a\u0631 \u0628\u062f\u0627\u0646\u06cc\u062f <code>if __name__ == \"__main__\"<\/code> \u0645\u0633\u062f\u0648\u062f \u06a9\u0646\u06cc\u062f\u060c \u0631\u0627\u0647\u0646\u0645\u0627\u06cc \u0645\u0627 \u0631\u0627 \u0628\u0631\u0631\u0633\u06cc \u06a9\u0646\u06cc\u062f \u0631\u0648\u06cc  \u0686\u06af\u0648\u0646\u0647 \u06a9\u0627\u0631 \u0645\u06cc \u06a9\u0646\u062f<\/p>\n<p>\u0634\u0645\u0627 \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0631\u0627 \u0645\u0637\u0627\u0628\u0642 \u062a\u0635\u0648\u06cc\u0631 \u0632\u06cc\u0631 \u0627\u062c\u0631\u0627 \u06a9\u0646\u06cc\u062f terminal \u0648 \u062e\u0631\u0648\u062c\u06cc \u0631\u0627 \u0628\u0647 \u0635\u0648\u0631\u062a \u0632\u06cc\u0631 \u062f\u0631\u06cc\u0627\u0641\u062a \u06a9\u0646\u06cc\u062f:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-meta\">$<\/span><span class=\"bash\"> python scraper.py<\/span>\n<\/code><\/pre>\n<pre><code class=\"hljs\">Web scraping has begun\nNow Scraping - http:\/\/books.toscrape.com\/catalogue\/page-1.html\nNow Scraping - http:\/\/books.toscrape.com\/catalogue\/page-2.html\nNow Scraping - http:\/\/books.toscrape.com\/catalogue\/page-3.html\n.\n.\n.\nNow Scraping - http:\/\/books.toscrape.com\/catalogue\/page-49.html\nNow Scraping - http:\/\/books.toscrape.com\/catalogue\/page-50.html\nWeb scraping is now complete!\n<\/code><\/pre>\n<p>\u062f\u0627\u062f\u0647 \u0647\u0627\u06cc \u062e\u0631\u0627\u0634\u06cc\u062f\u0647 \u0634\u062f\u0647 \u0631\u0627 \u0645\u06cc \u062a\u0648\u0627\u0646 \u062f\u0631 \u0641\u0647\u0631\u0633\u062a \u06a9\u0627\u0631\u06cc \u0641\u0639\u0644\u06cc \u0632\u06cc\u0631 \u0646\u0627\u0645 \u0641\u0627\u06cc\u0644 \u06cc\u0627\u0641\u062a <code>allBooks.csv<\/code>.  \u0646\u0645\u0648\u0646\u0647 \u0627\u06cc \u0627\u0632 \u0645\u062d\u062a\u0648\u0627\u06cc \u0641\u0627\u06cc\u0644 \u062f\u0631 \u0627\u06cc\u0646\u062c\u0627 \u0622\u0645\u062f\u0647 \u0627\u0633\u062a:<\/p>\n<pre><code class=\"hljs\">http:\/\/books.toscrape.com\/a-light-in-the-attic_1000\/index.html,http:\/\/books.toscrape.com\/catalogue\/media\/cache\/2c\/da\/2cdad67c44b002e7ead0cc35693c0e8b.jpg,A Light in the Attic,Three,51.77,In stock\nhttp:\/\/books.toscrape.com\/tipping-the-velvet_999\/index.html,http:\/\/books.toscrape.com\/catalogue\/media\/cache\/26\/0c\/260c6ae16bce31c8f8c95daddd9f4a1c.jpg,Tipping the Velvet,One,53.74,In stock\nhttp:\/\/books.toscrape.com\/soumission_998\/index.html,http:\/\/books.toscrape.com\/catalogue\/media\/cache\/3e\/ef\/3eef99c9d9adef34639f510662022830.jpg,Soumission,One,50.10,In stock\n<\/code><\/pre>\n<p>\u0622\u0641\u0631\u06cc\u0646!  \u0627\u06af\u0631 \u0645\u06cc \u062e\u0648\u0627\u0647\u06cc\u062f \u0628\u0647 \u06a9\u0644 \u06a9\u062f \u0627\u0633\u06a9\u0631\u0627\u067e\u0631 \u0646\u06af\u0627\u0647\u06cc \u0628\u06cc\u0646\u062f\u0627\u0632\u06cc\u062f\u060c \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u0622\u0646 \u0631\u0627 \u067e\u06cc\u062f\u0627 \u06a9\u0646\u06cc\u062f \u0631\u0648\u06cc <a href=\"https:\/\/github.com\/StackAbuse\/parsing-html-with-beautifulsoup-in-python\" rel=\"nofollow noopener\" target=\"_blank\">GitHub<\/a>.<\/p>\n<h2 id=\"conclusion\"><span class=\"ez-toc-section\" id=\"%d9%86%d8%aa%db%8c%d8%ac%d9%87\"><\/span>\u0646\u062a\u06cc\u062c\u0647<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>\u062f\u0631 \u0627\u06cc\u0646 \u0622\u0645\u0648\u0632\u0634\u060c \u0627\u062e\u0644\u0627\u0642 \u0646\u0648\u0634\u062a\u0646 \u0648\u0628 \u0627\u0633\u06a9\u0631\u0627\u067e\u0631\u0647\u0627\u06cc \u062e\u0648\u0628 \u0631\u0627 \u0622\u0645\u0648\u062e\u062a\u06cc\u0645.  \u0633\u067e\u0633 \u0627\u0632 Beautiful Soup \u0628\u0631\u0627\u06cc \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u062f\u0627\u062f\u0647 \u0647\u0627 \u0627\u0632 \u06cc\u06a9 \u0641\u0627\u06cc\u0644 HTML \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0648\u06cc\u0698\u06af\u06cc \u0647\u0627\u06cc \u0634\u06cc\u0621 Beautiful Soup \u0648 \u0631\u0648\u0634 \u0647\u0627\u06cc \u0645\u062e\u062a\u0644\u0641 \u0622\u0646 \u0645\u0627\u0646\u0646\u062f <code>find()<\/code>\u060c <code>find_all()<\/code> \u0648 <code>get_text()<\/code>.  \u0633\u067e\u0633 \u06cc\u06a9 \u0627\u0633\u06a9\u0631\u0627\u067e\u0631 \u0633\u0627\u062e\u062a\u06cc\u0645 \u06a9\u0647 \u0641\u0647\u0631\u0633\u062a \u06a9\u062a\u0627\u0628 \u0631\u0627 \u0628\u0647 \u0635\u0648\u0631\u062a \u0622\u0646\u0644\u0627\u06cc\u0646 \u0628\u0627\u0632\u06cc\u0627\u0628\u06cc \u0645\u06cc \u06a9\u0646\u062f \u0648 \u0628\u0647 CSV \u0635\u0627\u062f\u0631 \u0645\u06cc \u06a9\u0646\u062f.<\/p>\n<p>Web scraping \u06cc\u06a9 \u0645\u0647\u0627\u0631\u062a \u0645\u0641\u06cc\u062f \u0627\u0633\u062a \u06a9\u0647 \u0628\u0647 \u0641\u0639\u0627\u0644\u06cc\u062a\u200c\u0647\u0627\u06cc \u0645\u062e\u062a\u0644\u0641\u06cc \u0645\u0627\u0646\u0646\u062f \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u062f\u0627\u062f\u0647\u200c\u0647\u0627 \u0645\u0627\u0646\u0646\u062f API\u060c \u0627\u0646\u062c\u0627\u0645 QA \u06a9\u0645\u06a9 \u0645\u06cc\u200c\u06a9\u0646\u062f. \u0631\u0648\u06cc \u06cc\u06a9 \u0648\u0628\u200c\u0633\u0627\u06cc\u062a\u060c \u0622\u062f\u0631\u0633\u200c\u0647\u0627\u06cc \u062e\u0631\u0627\u0628 \u0631\u0627 \u0628\u0631\u0631\u0633\u06cc \u0645\u06cc\u200c\u06a9\u0646\u062f \u0631\u0648\u06cc \u06cc\u06a9 \u0648\u0628 \u0633\u0627\u06cc\u062a \u0648 \u0645\u0648\u0627\u0631\u062f \u062f\u06cc\u06af\u0631.  \u062e\u0631\u0627\u0634 \u0628\u0639\u062f\u06cc \u06a9\u0647 \u0642\u0631\u0627\u0631 \u0627\u0633\u062a \u0628\u0633\u0627\u0632\u06cc\u062f \u0686\u06cc\u0633\u062a\u061f<\/p>\n<\/div>\n<p><script>\n                        !function(f,b,e,v,n,t,s)\n                        {if(f.fbq)return;n=f.fbq=function(){n.callMethod?\n                        n.callMethod.apply(n,arguments):n.queue.push(arguments)};\n                        if(!f._fbq)f._fbq=n;n.push=n;n.loaded=!0;n.version='2.0';\n                        n.queue=();t=b.createElement(e);t.async=!0;\n                        t.src=v;s=b.getElementsByTagName(e)(0);\n                        s.parentNode.insertBefore(t,s)}(window, document,'script',\n                        'https:\/\/connect.facebook.net\/en_US\/fbevents.js');\n                        fbq('init', '525232124909042');\n                        fbq('track', 'PageView');\n                    <\/script>    (\u0628\u0631\u0686\u0633\u0628\u200c\u0647\u0627 \u0628\u0647 \u062a\u0631\u062c\u0645\u0647)# python<br \/>\n<br \/><br \/>\n<br \/>\u0645\u0646\u062a\u0634\u0631 \u0634\u062f\u0647 \u062f\u0631 1403-01-14 19:44:04<br \/>\n<\/p>\n\n\n<div class=\"kk-star-ratings kksr-auto kksr-align-center kksr-valign-bottom\"\n    data-payload='{&quot;align&quot;:&quot;center&quot;,&quot;id&quot;:&quot;15623&quot;,&quot;slug&quot;:&quot;default&quot;,&quot;valign&quot;:&quot;bottom&quot;,&quot;ignore&quot;:&quot;&quot;,&quot;reference&quot;:&quot;auto&quot;,&quot;class&quot;:&quot;&quot;,&quot;count&quot;:&quot;0&quot;,&quot;legendonly&quot;:&quot;&quot;,&quot;readonly&quot;:&quot;&quot;,&quot;score&quot;:&quot;0&quot;,&quot;starsonly&quot;:&quot;&quot;,&quot;best&quot;:&quot;5&quot;,&quot;gap&quot;:&quot;5&quot;,&quot;greet&quot;:&quot;\u0627\u0645\u062a\u06cc\u0627\u0632 \u0634\u0645\u0627 \u0628\u0647 \u0627\u06cc\u0646 \u0645\u0637\u0644\u0628&quot;,&quot;legend&quot;:&quot;0\\\/5 (0 \u0631\u0627\u06cc)&quot;,&quot;size&quot;:&quot;30&quot;,&quot;title&quot;:&quot;\u0631\u0627\u0647\u0646\u0645\u0627\u06cc \u062a\u062c\u0632\u06cc\u0647 HTML \u0628\u0627 BeautifulSoup \u062f\u0631 \u067e\u0627\u06cc\u062a\u0648\u0646&quot;,&quot;width&quot;:&quot;0&quot;,&quot;_legend&quot;:&quot;{score}\\\/{best} ({count} \u0631\u0627\u06cc)&quot;,&quot;font_factor&quot;:&quot;1.25&quot;}'>\n            \n<div class=\"kksr-stars\">\n    \n<div class=\"kksr-stars-inactive\">\n            <div class=\"kksr-star\" data-star=\"1\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" data-star=\"2\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" data-star=\"3\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" data-star=\"4\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" data-star=\"5\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n    <\/div>\n    \n<div class=\"kksr-stars-active\" style=\"width: 0px;\">\n            <div class=\"kksr-star\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n    <\/div>\n<\/div>\n                \n\n<div class=\"kksr-legend\" style=\"font-size: 24px;\">\n            <span class=\"kksr-muted\">\u0627\u0645\u062a\u06cc\u0627\u0632 \u0634\u0645\u0627 \u0628\u0647 \u0627\u06cc\u0646 \u0645\u0637\u0644\u0628<\/span>\n    <\/div>\n    <\/div>\n","protected":false},"excerpt":{"rendered":"<p><span class=\"span-reading-time rt-reading-time\" style=\"display: block;\"><span class=\"rt-label rt-prefix\">\u0632\u0645\u0627\u0646 \u0644\u0627\u0632\u0645 \u0628\u0631\u0627\u06cc \u0645\u0637\u0627\u0644\u0639\u0647: <\/span> <span class=\"rt-time\"> 7<\/span> <span class=\"rt-label rt-postfix\">\u062f\u0642\u06cc\u0642\u0647<\/span><\/span>\u0645\u0639\u0631\u0641\u06cc Web scraping \u0628\u0647 \u0635\u0648\u0631\u062a \u0628\u0631\u0646\u0627\u0645\u0647 \u0646\u0648\u06cc\u0633\u06cc \u0627\u0637\u0644\u0627\u0639\u0627\u062a \u0631\u0627 \u0627\u0632 \u0648\u0628 \u0633\u0627\u06cc\u062a \u0647\u0627\u06cc \u0645\u062e\u062a\u0644\u0641 \u062c\u0645\u0639 \u0622\u0648\u0631\u06cc \u0645\u06cc \u06a9\u0646\u062f. \u062f\u0631 \u062d\u0627\u0644\u06cc \u06a9\u0647 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647\u200c\u0647\u0627 \u0648 \u0686\u0627\u0631\u0686\u0648\u0628\u200c\u0647\u0627\u06cc \u0632\u06cc\u0627\u062f\u06cc \u0628\u0647 \u0632\u0628\u0627\u0646\u200c\u0647\u0627\u06cc \u0645\u062e\u062a\u0644\u0641 \u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f \u06a9\u0647 \u0645\u06cc\u200c\u062a\u0648\u0627\u0646\u0646\u062f \u062f\u0627\u062f\u0647\u200c\u0647\u0627\u06cc \u0648\u0628 \u0631\u0627 \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u06a9\u0646\u0646\u062f\u060c \u067e\u0627\u06cc\u062a\u0648\u0646 \u0628\u0647 \u062f\u0644\u06cc\u0644 \u06af\u0632\u06cc\u0646\u0647\u200c\u0647\u0627\u06cc \u0641\u0631\u0627\u0648\u0627\u0646\u06cc \u06a9\u0647 \u0628\u0631\u0627\u06cc \u0627\u0633\u06a9\u0631\u067e\u06cc\u0646\u06af \u0648\u0628 \u062f\u0627\u0631\u062f\u060c \u0645\u062f\u062a\u200c\u0647\u0627\u0633\u062a \u06a9\u0647 \u06cc\u06a9 \u0627\u0646\u062a\u062e\u0627\u0628 \u0645\u062d\u0628\u0648\u0628 \u0628\u0648\u062f\u0647 \u0627\u0633\u062a. \u0627\u06cc\u0646 [&hellip;]<\/p>\n","protected":false},"author":3,"featured_media":15624,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1743,620],"tags":[],"class_list":["post-15623","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-python","category-programming"],"acf":[],"_links":{"self":[{"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/posts\/15623","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/comments?post=15623"}],"version-history":[{"count":0,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/posts\/15623\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/media\/15624"}],"wp:attachment":[{"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/media?parent=15623"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/categories?post=15623"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/tags?post=15623"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}