{"id":16321,"date":"2024-01-23T13:42:52","date_gmt":"2024-01-23T10:12:52","guid":{"rendered":"https:\/\/rasanegar.com\/blog\/%da%a9%d8%a7%d8%b1-%d8%a8%d8%a7-pdf-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86-%d8%ae%d9%88%d8%a7%d9%86%d8%af%d9%86-%d9%88-%d8%aa%d9%82%d8%b3%db%8c%d9%85-%d8%b5%d9%81%d8%ad%d8%a7%d8%aa\/"},"modified":"2024-01-23T13:42:52","modified_gmt":"2024-01-23T10:12:52","slug":"%da%a9%d8%a7%d8%b1-%d8%a8%d8%a7-pdf-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86-%d8%ae%d9%88%d8%a7%d9%86%d8%af%d9%86-%d9%88-%d8%aa%d9%82%d8%b3%db%8c%d9%85-%d8%b5%d9%81%d8%ad%d8%a7%d8%aa","status":"publish","type":"post","link":"https:\/\/rasanegaar.com\/blog\/%da%a9%d8%a7%d8%b1-%d8%a8%d8%a7-pdf-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86-%d8%ae%d9%88%d8%a7%d9%86%d8%af%d9%86-%d9%88-%d8%aa%d9%82%d8%b3%db%8c%d9%85-%d8%b5%d9%81%d8%ad%d8%a7%d8%aa\/","title":{"rendered":"\u06a9\u0627\u0631 \u0628\u0627 PDF \u062f\u0631 \u067e\u0627\u06cc\u062a\u0648\u0646: \u062e\u0648\u0627\u0646\u062f\u0646 \u0648 \u062a\u0642\u0633\u06cc\u0645 \u0635\u0641\u062d\u0627\u062a"},"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\/%da%a9%d8%a7%d8%b1-%d8%a8%d8%a7-pdf-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86-%d8%ae%d9%88%d8%a7%d9%86%d8%af%d9%86-%d9%88-%d8%aa%d9%82%d8%b3%db%8c%d9%85-%d8%b5%d9%81%d8%ad%d8%a7%d8%aa\/#%d9%81%d8%b1%d9%85%d8%aa_%d8%b3%d9%86%d8%af_pdf\" >\u0641\u0631\u0645\u062a \u0633\u0646\u062f PDF<\/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\/%da%a9%d8%a7%d8%b1-%d8%a8%d8%a7-pdf-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86-%d8%ae%d9%88%d8%a7%d9%86%d8%af%d9%86-%d9%88-%d8%aa%d9%82%d8%b3%db%8c%d9%85-%d8%b5%d9%81%d8%ad%d8%a7%d8%aa\/#%d9%be%d8%b1%d8%af%d8%a7%d8%b2%d8%b4_%d8%a7%d8%b3%d9%86%d8%a7%d8%af_pdf\" >\u067e\u0631\u062f\u0627\u0632\u0634 \u0627\u0633\u0646\u0627\u062f PDF<\/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\/%da%a9%d8%a7%d8%b1-%d8%a8%d8%a7-pdf-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86-%d8%ae%d9%88%d8%a7%d9%86%d8%af%d9%86-%d9%88-%d8%aa%d9%82%d8%b3%db%8c%d9%85-%d8%b5%d9%81%d8%ad%d8%a7%d8%aa\/#%d8%aa%d9%82%d8%b3%db%8c%d9%85_pdf_%d8%a8%d9%87_%d8%b5%d9%81%d8%ad%d8%a7%d8%aa_%d8%a8%d8%a7_pypdf2\" >\u062a\u0642\u0633\u06cc\u0645 PDF \u0628\u0647 \u0635\u0641\u062d\u0627\u062a \u0628\u0627 PyPDF2<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/rasanegaar.com\/blog\/%da%a9%d8%a7%d8%b1-%d8%a8%d8%a7-pdf-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86-%d8%ae%d9%88%d8%a7%d9%86%d8%af%d9%86-%d9%88-%d8%aa%d9%82%d8%b3%db%8c%d9%85-%d8%b5%d9%81%d8%ad%d8%a7%d8%aa\/#%d9%87%d9%85%d9%87_%d8%b5%d9%81%d8%ad%d8%a7%d8%aa_%d8%ad%d8%a7%d9%88%db%8c_%d9%85%d8%aa%d9%86_%d8%b1%d8%a7_%d9%be%db%8c%d8%af%d8%a7_%da%a9%d9%86%db%8c%d8%af\" >\u0647\u0645\u0647 \u0635\u0641\u062d\u0627\u062a \u062d\u0627\u0648\u06cc \u0645\u062a\u0646 \u0631\u0627 \u067e\u06cc\u062f\u0627 \u06a9\u0646\u06cc\u062f<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/rasanegaar.com\/blog\/%da%a9%d8%a7%d8%b1-%d8%a8%d8%a7-pdf-%d8%af%d8%b1-%d9%be%d8%a7%db%8c%d8%aa%d9%88%d9%86-%d8%ae%d9%88%d8%a7%d9%86%d8%af%d9%86-%d9%88-%d8%aa%d9%82%d8%b3%db%8c%d9%85-%d8%b5%d9%81%d8%ad%d8%a7%d8%aa\/#%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<p><em>\u0627\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647 \u0627\u0648\u0644\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647 \u0627\u0632 \u0645\u062c\u0645\u0648\u0639\u0647 \u0627\u0633\u062a \u0631\u0648\u06cc \u06a9\u0627\u0631 \u0628\u0627 PDF \u062f\u0631 \u067e\u0627\u06cc\u062a\u0648\u0646:<\/em><\/p>\n<h2 id=\"thepdfdocumentformat\"><span class=\"ez-toc-section\" id=\"%d9%81%d8%b1%d9%85%d8%aa_%d8%b3%d9%86%d8%af_pdf\"><\/span>\u0641\u0631\u0645\u062a \u0633\u0646\u062f PDF<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>\u0627\u0645\u0631\u0648\u0632\u0647\u060c \u0641\u0631\u0645\u062a \u0633\u0646\u062f \u0642\u0627\u0628\u0644 \u062d\u0645\u0644 (PDF) \u0628\u0647 \u0631\u0627\u06cc\u062c \u062a\u0631\u06cc\u0646 \u0641\u0631\u0645\u062a \u0647\u0627\u06cc \u062f\u0627\u062f\u0647 \u062a\u0639\u0644\u0642 \u062f\u0627\u0631\u062f.  \u062f\u0631 \u0633\u0627\u0644 1990\u060c \u0633\u0627\u062e\u062a\u0627\u0631 \u06cc\u06a9 \u0633\u0646\u062f PDF \u062a\u0648\u0633\u0637 Adobe \u062a\u0639\u0631\u06cc\u0641 \u0634\u062f.  \u0627\u06cc\u062f\u0647 \u067e\u0634\u062a \u0641\u0631\u0645\u062a PDF \u0627\u06cc\u0646 \u0627\u0633\u062a \u06a9\u0647 \u062f\u0627\u062f\u0647 \u0647\u0627 \/ \u0627\u0633\u0646\u0627\u062f \u0627\u0631\u0633\u0627\u0644 \u0634\u062f\u0647 \u0628\u0631\u0627\u06cc \u0647\u0631 \u062f\u0648 \u0637\u0631\u0641\u06cc \u06a9\u0647 \u062f\u0631 \u0627\u0631\u062a\u0628\u0627\u0637 \u0647\u0633\u062a\u0646\u062f \u062f\u0642\u06cc\u0642\u0627\u064b \u06cc\u06a9\u0633\u0627\u0646 \u0628\u0647 \u0646\u0638\u0631 \u0645\u06cc \u0631\u0633\u0646\u062f. process &#8211; \u062e\u0627\u0644\u0642\u060c \u0646\u0648\u06cc\u0633\u0646\u062f\u0647 \u06cc\u0627 \u0641\u0631\u0633\u062a\u0646\u062f\u0647 \u0648 \u06af\u06cc\u0631\u0646\u062f\u0647.  PDF \u062c\u0627\u0646\u0634\u06cc\u0646 \u0622\u0646 \u0627\u0633\u062a <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/en.wikipedia.org\/wiki\/PostScript\">\u067e\u0633\u062a \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a<\/a> \u0641\u0631\u0645\u062a\u060c \u0648 \u0627\u0633\u062a\u0627\u0646\u062f\u0627\u0631\u062f \u0634\u062f\u0647 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/www.iso.org\/standard\/63534.html\">ISO 32000-2:2017<\/a>.<\/p>\n<h2 id=\"processingpdfdocuments\"><span class=\"ez-toc-section\" id=\"%d9%be%d8%b1%d8%af%d8%a7%d8%b2%d8%b4_%d8%a7%d8%b3%d9%86%d8%a7%d8%af_pdf\"><\/span>\u067e\u0631\u062f\u0627\u0632\u0634 \u0627\u0633\u0646\u0627\u062f PDF<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>\u0628\u0631\u0627\u06cc \u0644\u06cc\u0646\u0648\u06a9\u0633 \u0627\u0628\u0632\u0627\u0631\u0647\u0627\u06cc \u062e\u0637 \u0641\u0631\u0645\u0627\u0646 \u0642\u062f\u0631\u062a\u0645\u0646\u062f\u06cc \u0645\u0627\u0646\u0646\u062f <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/www.pdflabs.com\/tools\/pdftk-the-pdf-toolkit\/\">pdftk<\/a> \u0648 <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/pdfgrep.org\/\">pdfgrep<\/a>.  \u0628\u0647\u200c\u0639\u0646\u0648\u0627\u0646 \u06cc\u06a9 \u062a\u0648\u0633\u0639\u0647\u200c\u062f\u0647\u0646\u062f\u0647\u060c \u0647\u06cc\u062c\u0627\u0646 \u0632\u06cc\u0627\u062f\u06cc \u0628\u0631\u0627\u06cc \u0633\u0627\u062e\u062a\u0646 \u0646\u0631\u0645\u200c\u0627\u0641\u0632\u0627\u0631 \u0634\u062e\u0635\u06cc \u0634\u0645\u0627 \u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f \u06a9\u0647 \u0645\u0628\u062a\u0646\u06cc \u0628\u0631 \u0622\u0646 \u0627\u0633\u062a \u0631\u0648\u06cc \u067e\u0627\u06cc\u062a\u0648\u0646 \u0648 \u0627\u0632 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0647\u0627\u06cc PDF \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u06a9\u0646\u062f \u06a9\u0647 \u0628\u0647 \u0635\u0648\u0631\u062a \u0631\u0627\u06cc\u06af\u0627\u0646 \u062f\u0631 \u062f\u0633\u062a\u0631\u0633 \u0647\u0633\u062a\u0646\u062f.<\/p>\n<p>\u0627\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647 \u0622\u063a\u0627\u0632 \u06cc\u06a9 \u0633\u0631\u06cc \u06a9\u0648\u0686\u06a9 \u0627\u0633\u062a \u0648 \u0627\u06cc\u0646 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0647\u0627\u06cc \u0645\u0641\u06cc\u062f \u067e\u0627\u06cc\u062a\u0648\u0646 \u0631\u0627 \u067e\u0648\u0634\u0634 \u0645\u06cc \u062f\u0647\u062f.  \u062f\u0631 \u0642\u0633\u0645\u062a \u0627\u0648\u0644 \u062a\u0645\u0631\u06a9\u0632 \u062e\u0648\u0627\u0647\u06cc\u0645 \u06a9\u0631\u062f \u0631\u0648\u06cc \u062f\u0633\u062a\u06a9\u0627\u0631\u06cc \u0641\u0627\u06cc\u0644 \u0647\u0627\u06cc PDF \u0645\u0648\u062c\u0648\u062f  \u0634\u0645\u0627 \u06cc\u0627\u062f \u062e\u0648\u0627\u0647\u06cc\u062f \u06af\u0631\u0641\u062a \u06a9\u0647 \u0686\u06af\u0648\u0646\u0647 \u0645\u062d\u062a\u0648\u0627 (\u0647\u0645 \u0645\u062a\u0646 \u0648 \u0647\u0645 \u0639\u06a9\u0633) \u0631\u0627 \u0628\u062e\u0648\u0627\u0646\u06cc\u062f \u0648 \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u06a9\u0646\u06cc\u062f\u060c \u0635\u0641\u062d\u0627\u062a \u062a\u06a9\u06cc \u0631\u0627 \u0628\u0686\u0631\u062e\u0627\u0646\u06cc\u062f \u0648 \u0627\u0633\u0646\u0627\u062f \u0631\u0627 \u0628\u0647 \u0635\u0641\u062d\u0627\u062a \u062c\u062f\u0627\u06af\u0627\u0646\u0647 \u0622\u0646 \u062a\u0642\u0633\u06cc\u0645 \u06a9\u0646\u06cc\u062f.  \u0642\u0633\u0645\u062a \u062f\u0648\u0645 \u0627\u0636\u0627\u0641\u0647 \u06a9\u0631\u062f\u0646 \u0648\u0627\u062a\u0631\u0645\u0627\u0631\u06a9 \u0628\u0631 \u0627\u0633\u0627\u0633 \u0631\u0627 \u067e\u0648\u0634\u0634 \u062e\u0648\u0627\u0647\u062f \u062f\u0627\u062f \u0631\u0648\u06cc \u067e\u0648\u0634\u0634 \u0647\u0627.  \u0628\u062e\u0634 \u0633\u0648\u0645 \u0645\u0646\u062d\u0635\u0631\u0627\u064b \u062a\u0645\u0631\u06a9\u0632 \u062e\u0648\u0627\u0647\u062f \u062f\u0627\u0634\u062a \u0631\u0648\u06cc \u0646\u0648\u0634\u062a\u0646\/\u0627\u06cc\u062c\u0627\u062f PDF\u060c \u0648 \u0647\u0645\u0686\u0646\u06cc\u0646 \u0634\u0627\u0645\u0644 \u062d\u0630\u0641 \u0648 \u062a\u0631\u06a9\u06cc\u0628 \u0645\u062c\u062f\u062f \u0635\u0641\u062d\u0627\u062a \u0645\u0646\u0641\u0631\u062f \u062f\u0631 \u06cc\u06a9 \u0633\u0646\u062f \u062c\u062f\u06cc\u062f \u0645\u06cc \u0634\u0648\u062f.<\/p>\n<p>\u0637\u06cc\u0641 \u0631\u0627\u0647\u200c\u062d\u0644\u200c\u0647\u0627\u06cc \u0645\u0648\u062c\u0648\u062f \u0628\u0631\u0627\u06cc \u0627\u0628\u0632\u0627\u0631\u0647\u0627\u060c \u0645\u0627\u0698\u0648\u0644\u200c\u0647\u0627 \u0648 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647\u200c\u0647\u0627\u06cc \u067e\u06cc\u200c\u062f\u06cc\u200c\u0627\u0641 \u0645\u0631\u062a\u0628\u0637 \u0628\u0627 \u067e\u0627\u06cc\u062a\u0648\u0646 \u06a9\u0645\u06cc \u06af\u06cc\u062c\u200c\u06a9\u0646\u0646\u062f\u0647 \u0627\u0633\u062a \u0648 \u06a9\u0645\u06cc \u0637\u0648\u0644 \u0645\u06cc\u200c\u06a9\u0634\u062f \u062a\u0627 \u0628\u0641\u0647\u0645\u06cc\u0645 \u0686\u0647 \u0686\u06cc\u0632\u06cc \u0686\u06cc\u0633\u062a \u0648 \u06a9\u062f\u0627\u0645 \u067e\u0631\u0648\u0698\u0647\u200c\u0647\u0627 \u0628\u0647 \u0637\u0648\u0631 \u0645\u062f\u0627\u0648\u0645 \u0646\u06af\u0647\u062f\u0627\u0631\u06cc \u0645\u06cc\u200c\u0634\u0648\u0646\u062f.  \u0645\u0633\u062a\u0642\u0631 \u0631\u0648\u06cc \u062a\u062d\u0642\u06cc\u0642\u0627\u062a \u0645\u0627 \u0627\u06cc\u0646\u0647\u0627 \u0646\u0627\u0645\u0632\u062f\u0647\u0627\u06cc\u06cc \u0647\u0633\u062a\u0646\u062f \u06a9\u0647 \u0628\u0647 \u0631\u0648\u0632 \u0647\u0633\u062a\u0646\u062f:<\/p>\n<ul>\n<li>\n<p><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/pypi.org\/project\/PyPDF2\/\">PyPDF2<\/a>: \u06cc\u06a9 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u067e\u0627\u06cc\u062a\u0648\u0646 \u0628\u0631\u0627\u06cc \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u0627\u0637\u0644\u0627\u0639\u0627\u062a \u0648 \u0645\u062d\u062a\u0648\u0627\u06cc \u0627\u0633\u0646\u0627\u062f\u060c \u062a\u0642\u0633\u06cc\u0645 \u0627\u0633\u0646\u0627\u062f page-\u062a\u0648\u0633\u0637-page\u060c \u0627\u0633\u0646\u0627\u062f \u0631\u0627 \u0627\u062f\u063a\u0627\u0645 \u06a9\u0646\u06cc\u062f\u060c \u0635\u0641\u062d\u0627\u062a \u0631\u0627 \u0628\u0631\u0634 \u062f\u0647\u06cc\u062f \u0648 \u0648\u0627\u062a\u0631\u0645\u0627\u0631\u06a9 \u0627\u0636\u0627\u0641\u0647 \u06a9\u0646\u06cc\u062f.  PyPDF2 \u0627\u0632 \u0627\u0633\u0646\u0627\u062f \u0631\u0645\u0632\u06af\u0630\u0627\u0631\u06cc \u0646\u0634\u062f\u0647 \u0648 \u0631\u0645\u0632\u06af\u0630\u0627\u0631\u06cc \u0634\u062f\u0647 \u067e\u0634\u062a\u06cc\u0628\u0627\u0646\u06cc \u0645\u06cc \u06a9\u0646\u062f.<\/p>\n<\/li>\n<li>\n<p><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/euske.github.io\/pdfminer\/index.html\">PDFMiner<\/a>: \u0628\u0647 \u0637\u0648\u0631 \u06a9\u0627\u0645\u0644 \u062f\u0631 \u067e\u0627\u06cc\u062a\u0648\u0646 \u0646\u0648\u0634\u062a\u0647 \u0634\u062f\u0647 \u0627\u0633\u062a \u0648 \u0628\u0631\u0627\u06cc Python 2.4 \u0628\u0647 \u062e\u0648\u0628\u06cc \u06a9\u0627\u0631 \u0645\u06cc \u06a9\u0646\u062f.  \u0628\u0631\u0627\u06cc \u067e\u0627\u06cc\u062a\u0648\u0646 3\u060c \u0627\u0632 \u0628\u0633\u062a\u0647 \u06a9\u0644\u0648\u0646 \u0634\u062f\u0647 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0646\u06cc\u062f <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/github.com\/pdfminer\/pdfminer.six\">PDFMiner.six<\/a>.  \u0647\u0631 \u062f\u0648 \u0628\u0633\u062a\u0647 \u0628\u0647 \u0634\u0645\u0627 \u0627\u0645\u06a9\u0627\u0646 \u062a\u062c\u0632\u06cc\u0647\u060c \u062a\u062c\u0632\u06cc\u0647 \u0648 \u062a\u062d\u0644\u06cc\u0644 \u0648 \u062a\u0628\u062f\u06cc\u0644 \u0627\u0633\u0646\u0627\u062f PDF \u0631\u0627 \u0645\u06cc \u062f\u0647\u0646\u062f.  \u0627\u06cc\u0646 \u0634\u0627\u0645\u0644 \u067e\u0634\u062a\u06cc\u0628\u0627\u0646\u06cc \u0627\u0632 PDF 1.7 \u0648 \u0647\u0645\u0686\u0646\u06cc\u0646 \u0632\u0628\u0627\u0646 \u0647\u0627\u06cc CJK (\u0686\u06cc\u0646\u06cc\u060c \u0698\u0627\u067e\u0646\u06cc \u0648 \u06a9\u0631\u0647 \u0627\u06cc) \u0648 \u0627\u0646\u0648\u0627\u0639 \u0641\u0648\u0646\u062a (Type1\u060c TrueType\u060c Type3\u060c \u0648 CID) \u0645\u06cc \u0634\u0648\u062f.<\/p>\n<\/li>\n<li>\n<p><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/github.com\/jcushman\/pdfquery\">PDFQuery<\/a>: \u062e\u0648\u062f \u0631\u0627 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u06cc\u06a9 &#8220;\u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u062e\u0631\u0627\u0634 \u067e\u06cc \u062f\u06cc \u0627\u0641 \u0633\u0631\u06cc\u0639 \u0648 \u062f\u0648\u0633\u062a\u0627\u0646\u0647&#8221; \u062a\u0648\u0635\u06cc\u0641 \u0645\u06cc \u06a9\u0646\u062f \u06a9\u0647 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u06cc\u06a9 \u0628\u0633\u062a\u0647 \u0628\u0646\u062f\u06cc \u062f\u0631 \u0627\u0637\u0631\u0627\u0641 PDFMiner\u060c lxml \u0648 <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/pypi.org\/project\/pyquery\/\">\u06af\u06cc\u062c \u06a9\u0631\u062f\u0646<\/a>.  \u0647\u062f\u0641 \u0637\u0631\u0627\u062d\u06cc \u0622\u0646 \u00ab\u0627\u0633\u062a\u062e\u0631\u0627\u062c \u0645\u0637\u0645\u0626\u0646 \u062f\u0627\u062f\u0647\u200c\u0647\u0627 \u0627\u0632 \u0645\u062c\u0645\u0648\u0639\u0647\u200c\u0647\u0627\u06cc PDF \u0628\u0627 \u06a9\u0645\u062a\u0631\u06cc\u0646 \u06a9\u062f \u0645\u0645\u06a9\u0646 \u0627\u0633\u062a\u00bb.<\/p>\n<\/li>\n<li>\n<p><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/github.com\/chezou\/tabula-py\">\u062c\u062f\u0648\u0644-py<\/a>: \u0627\u06cc\u0646 \u06cc\u06a9 \u0631\u0648\u06a9\u0634 \u0633\u0627\u062f\u0647 \u067e\u0627\u06cc\u062a\u0648\u0646 \u0627\u0633\u062a <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/github.com\/tabulapdf\/tabula-java\">Tabula-java<\/a>\u060c \u06a9\u0647 \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u062c\u062f\u0627\u0648\u0644 \u0631\u0627 \u0627\u0632 PDF \u0628\u062e\u0648\u0627\u0646\u062f \u0648 \u0622\u0646\u0647\u0627 \u0631\u0627 \u0628\u0647 Pandas DataFrames \u062a\u0628\u062f\u06cc\u0644 \u06a9\u0646\u062f.  \u0647\u0645\u0686\u0646\u06cc\u0646 \u0634\u0645\u0627 \u0631\u0627 \u0642\u0627\u062f\u0631 \u0645\u06cc \u0633\u0627\u0632\u062f \u06a9\u0647 \u06cc\u06a9 \u0641\u0627\u06cc\u0644 PDF \u0631\u0627 \u0628\u0647 \u06cc\u06a9 \u0641\u0627\u06cc\u0644 CSV\/TSV\/JSON \u062a\u0628\u062f\u06cc\u0644 \u06a9\u0646\u06cc\u062f.<\/p>\n<\/li>\n<li>\n<p><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/github.com\/alephdata\/pdflib\">pdflib<\/a> \u0628\u0631\u0627\u06cc \u067e\u0627\u06cc\u062a\u0648\u0646: \u067e\u0633\u0648\u0646\u062f\u06cc \u0627\u0632 <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/poppler.freedesktop.org\/\">\u067e\u0648\u067e\u0644\u0631<\/a> \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0627\u06cc \u06a9\u0647 \u067e\u06cc\u0648\u0646\u062f\u0647\u0627\u06cc \u067e\u0627\u06cc\u062a\u0648\u0646 \u0631\u0627 \u0628\u0631\u0627\u06cc \u0622\u0646 \u0627\u0631\u0627\u0626\u0647 \u0645\u06cc \u062f\u0647\u062f.  \u0627\u06cc\u0646 \u0628\u0647 \u0634\u0645\u0627 \u0627\u0645\u06a9\u0627\u0646 \u0645\u06cc \u062f\u0647\u062f \u0627\u0633\u0646\u0627\u062f PDF \u0631\u0627 \u062a\u062c\u0632\u06cc\u0647\u060c \u062a\u062c\u0632\u06cc\u0647 \u0648 \u062a\u062d\u0644\u06cc\u0644 \u0648 \u062a\u0628\u062f\u06cc\u0644 \u06a9\u0646\u06cc\u062f.  \u0646\u0628\u0627\u06cc\u062f \u0628\u0627 \u0622\u0646 \u0627\u0634\u062a\u0628\u0627\u0647 \u06af\u0631\u0641\u062a\u0647 \u0634\u0648\u062f <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/www.pdflib.com\/\">\u0622\u0648\u06cc\u0632 \u062a\u062c\u0627\u0631\u06cc<\/a> \u06a9\u0647 \u0647\u0645\u06cc\u0646 \u0646\u0627\u0645 \u0631\u0627 \u062f\u0627\u0631\u062f<\/p>\n<\/li>\n<li>\n<p><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/pyfpdf.readthedocs.io\/en\/latest\/\">PyFPDF<\/a>: \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0627\u06cc \u0628\u0631\u0627\u06cc \u062a\u0648\u0644\u06cc\u062f \u0627\u0633\u0646\u0627\u062f PDF \u062a\u062d\u062a \u067e\u0627\u06cc\u062a\u0648\u0646.  \u0645\u0646\u062a\u0642\u0644 \u0634\u062f\u0647 \u0627\u0632 <a rel=\"nofollow noopener\" target=\"_blank\" href=\"http:\/\/www.fpdf.org\/\">FPDF<\/a> \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 PHP\u060c \u06cc\u06a9 \u062c\u0627\u06cc\u06af\u0632\u06cc\u0646 \u0634\u0646\u0627\u062e\u062a\u0647 \u0634\u062f\u0647 \u067e\u0633\u0648\u0646\u062f PDFlib \u0628\u0627 \u0645\u062b\u0627\u0644 \u0647\u0627\u060c \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0647\u0627 \u0648 \u0645\u0634\u062a\u0642\u0627\u062a \u0641\u0631\u0627\u0648\u0627\u0646.<\/p>\n<\/li>\n<li>\n<p><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/pdftables.com\/\">\u062c\u062f\u0627\u0648\u0644 PDF<\/a>: \u06cc\u06a9 \u0633\u0631\u0648\u06cc\u0633 \u062a\u062c\u0627\u0631\u06cc \u06a9\u0647 \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u0627\u0632 \u062c\u062f\u0627\u0648\u0644 \u0631\u0627 \u0628\u0647 \u0635\u0648\u0631\u062a \u0633\u0646\u062f PDF \u0627\u0631\u0627\u0626\u0647 \u0645\u06cc \u062f\u0647\u062f.  \u06cc\u06a9 API \u0627\u0631\u0627\u0626\u0647 \u0645\u06cc \u062f\u0647\u062f \u062a\u0627 PDFTables \u0631\u0627 \u0628\u062a\u0648\u0627\u0646 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 SAAS \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0631\u062f.<\/p>\n<\/li>\n<li>\n<p><a rel=\"nofollow noopener\" target=\"_blank\" href=\"http:\/\/pyx.sourceforge.net\/index.html\">PyX<\/a> &#8211; \u0628\u0633\u062a\u0647 \u06af\u0631\u0627\u0641\u06cc\u06a9\u06cc \u067e\u0627\u06cc\u062a\u0648\u0646: PyX \u06cc\u06a9 \u0628\u0633\u062a\u0647 \u067e\u0627\u06cc\u062a\u0648\u0646 \u0628\u0631\u0627\u06cc \u0627\u06cc\u062c\u0627\u062f \u0641\u0627\u06cc\u0644\u200c\u0647\u0627\u06cc PostScript\u060c PDF \u0648 SVG \u0627\u0633\u062a.  \u0627\u06cc\u0646 \u0627\u0646\u062a\u0632\u0627\u0639\u06cc \u0627\u0632 \u0645\u062f\u0644 \u062a\u0631\u0633\u06cc\u0645 PostScript \u0631\u0627 \u0628\u0627 \u0631\u0627\u0628\u0637 TeX\/LaTeX \u062a\u0631\u06a9\u06cc\u0628 \u0645\u06cc \u06a9\u0646\u062f.  \u0648\u0638\u0627\u06cc\u0641 \u067e\u06cc\u0686\u06cc\u062f\u0647 \u0627\u06cc \u0645\u0627\u0646\u0646\u062f \u0627\u06cc\u062c\u0627\u062f \u0646\u0645\u0648\u062f\u0627\u0631\u0647\u0627\u06cc \u062f\u0648\u0628\u0639\u062f\u06cc \u0648 \u0633\u0647 \u0628\u0639\u062f\u06cc \u0628\u0627 \u06a9\u06cc\u0641\u06cc\u062a \u0622\u0645\u0627\u062f\u0647 \u0627\u0646\u062a\u0634\u0627\u0631 \u0627\u0632 \u0627\u06cc\u0646 \u0645\u0648\u0627\u0631\u062f \u0627\u0648\u0644\u06cc\u0647 \u0633\u0627\u062e\u062a\u0647 \u0634\u062f\u0647 \u0627\u0633\u062a.<\/p>\n<\/li>\n<li>\n<p><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/www.reportlab.com\/\">ReportLab<\/a>: \u06cc\u06a9 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u062c\u0627\u0647 \u0637\u0644\u0628\u0627\u0646\u0647 \u0628\u0627 \u0642\u062f\u0631\u062a \u0635\u0646\u0639\u062a\u06cc \u06a9\u0647 \u0639\u0645\u062f\u062a\u0627\u064b \u0645\u062a\u0645\u0631\u06a9\u0632 \u0634\u062f\u0647 \u0627\u0633\u062a \u0631\u0648\u06cc \u0627\u06cc\u062c\u0627\u062f \u062f\u0642\u06cc\u0642 \u0627\u0633\u0646\u0627\u062f PDF  \u0628\u0647 \u0635\u0648\u0631\u062a \u0622\u0632\u0627\u062f \u062f\u0631 \u062f\u0633\u062a\u0631\u0633 \u0627\u0633\u062a Source \u0646\u0633\u062e\u0647 \u0648 \u0647\u0645\u0686\u0646\u06cc\u0646 \u06cc\u06a9 \u0646\u0633\u062e\u0647 \u062a\u062c\u0627\u0631\u06cc \u0648 \u067e\u06cc\u0634\u0631\u0641\u062a\u0647 \u0628\u0647 \u0646\u0627\u0645 ReportLab PLUS.<\/p>\n<\/li>\n<li>\n<p><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/github.com\/pymupdf\/PyMuPDF\">PyMuPDF<\/a> (\u0645\u0639\u0631\u0648\u0641 \u0628\u0647 &#8220;fitz&#8221;): \u0627\u062a\u0635\u0627\u0644\u0627\u062a \u067e\u0627\u06cc\u062a\u0648\u0646 \u0628\u0631\u0627\u06cc MuPDF\u060c \u06a9\u0647 \u06cc\u06a9 \u0646\u0645\u0627\u06cc\u0634\u06af\u0631 PDF \u0648 XPS \u0633\u0628\u06a9 \u0648\u0632\u0646 \u0627\u0633\u062a.  \u0627\u06cc\u0646 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0645\u06cc\u200c\u062a\u0648\u0627\u0646\u062f \u0628\u0647 \u0641\u0627\u06cc\u0644\u200c\u0647\u0627 \u062f\u0631 \u0641\u0631\u0645\u062a\u200c\u0647\u0627\u06cc PDF\u060c XPS\u060c OpenXPS\u060c epub\u060c \u06a9\u0645\u06cc\u06a9 \u0648 \u06a9\u062a\u0627\u0628\u200c\u0647\u0627\u06cc \u062a\u062e\u06cc\u0644\u06cc \u062f\u0633\u062a\u0631\u0633\u06cc \u062f\u0627\u0634\u062a\u0647 \u0628\u0627\u0634\u062f \u0648 \u0628\u0647 \u062e\u0627\u0637\u0631 \u0639\u0645\u0644\u06a9\u0631\u062f \u0639\u0627\u0644\u06cc \u0648 \u06a9\u06cc\u0641\u06cc\u062a \u0631\u0646\u062f\u0631 \u0628\u0627\u0644\u0627 \u0634\u0647\u0631\u062a \u062f\u0627\u0631\u062f.<\/p>\n<\/li>\n<li>\n<p><a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/pypi.org\/project\/pdfrw\/\">pdfrw<\/a>: \u06cc\u06a9 \u062a\u062c\u0632\u06cc\u0647 \u06a9\u0646\u0646\u062f\u0647 PDF \u062e\u0627\u0644\u0635 \u0645\u0628\u062a\u0646\u06cc \u0628\u0631 \u067e\u0627\u06cc\u062a\u0648\u0646 \u0628\u0631\u0627\u06cc \u062e\u0648\u0627\u0646\u062f\u0646 \u0648 \u0646\u0648\u0634\u062a\u0646 PDF.  \u0641\u0631\u0645\u062a \u0647\u0627\u06cc \u0628\u0631\u062f\u0627\u0631\u06cc \u0631\u0627 \u0628\u062f\u0648\u0646 \u0634\u0637\u0631\u0646\u062c\u06cc \u0628\u0647 \u0637\u0648\u0631 \u0635\u0627\u062f\u0642\u0627\u0646\u0647 \u0628\u0627\u0632\u062a\u0648\u0644\u06cc\u062f \u0645\u06cc \u06a9\u0646\u062f.  \u062f\u0631 \u0627\u0631\u062a\u0628\u0627\u0637 \u0628\u0627 ReportLab\u060c \u0628\u0647 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u062c\u062f\u062f \u0627\u0632 \u0628\u062e\u0634 \u0647\u0627\u06cc\u06cc \u0627\u0632 PDF \u0647\u0627\u06cc \u0645\u0648\u062c\u0648\u062f \u062f\u0631 PDF \u0647\u0627\u06cc \u062c\u062f\u06cc\u062f \u0627\u06cc\u062c\u0627\u062f \u0634\u062f\u0647 \u0628\u0627 ReportLab \u06a9\u0645\u06a9 \u0645\u06cc \u06a9\u0646\u062f.<\/p>\n<\/li>\n<\/ul>\n<table class=\"table table-striped\">\n<thead>\n<tr>\n<th>\u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647<\/th>\n<th>\u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0628\u0631\u0627\u06cc<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>PyPDF2<\/td>\n<td>\u062e\u0648\u0627\u0646\u062f\u0646<\/td>\n<\/tr>\n<tr>\n<td>PyMuPDF<\/td>\n<td>\u062e\u0648\u0627\u0646\u062f\u0646<\/td>\n<\/tr>\n<tr>\n<td>pdflib<\/td>\n<td>\u062e\u0648\u0627\u0646\u062f\u0646<\/td>\n<\/tr>\n<tr>\n<td>\u062c\u062f\u0627\u0648\u0644 PDF<\/td>\n<td>\u062e\u0648\u0627\u0646\u062f\u0646<\/td>\n<\/tr>\n<tr>\n<td>\u062c\u062f\u0648\u0644-py<\/td>\n<td>\u062e\u0648\u0627\u0646\u062f\u0646<\/td>\n<\/tr>\n<tr>\n<td>PDFMiner.six<\/td>\n<td>\u062e\u0648\u0627\u0646\u062f\u0646<\/td>\n<\/tr>\n<tr>\n<td>PDFQuery<\/td>\n<td>\u062e\u0648\u0627\u0646\u062f\u0646<\/td>\n<\/tr>\n<tr>\n<td>pdfrw<\/td>\n<td>\u062e\u0648\u0627\u0646\u062f\u0646\u060c \u0646\u0648\u0634\u062a\u0646 \/ \u0627\u06cc\u062c\u0627\u062f<\/td>\n<\/tr>\n<tr>\n<td>Reportlab<\/td>\n<td>\u0646\u0648\u0634\u062a\u0646 \/ \u0627\u06cc\u062c\u0627\u062f<\/td>\n<\/tr>\n<tr>\n<td>PyX<\/td>\n<td>\u0646\u0648\u0634\u062a\u0646 \/ \u0627\u06cc\u062c\u0627\u062f<\/td>\n<\/tr>\n<tr>\n<td>PyFPDF<\/td>\n<td>\u0646\u0648\u0634\u062a\u0646 \/ \u0627\u06cc\u062c\u0627\u062f<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>\u062f\u0631 \u0632\u06cc\u0631 \u0628\u0647 \u062a\u0645\u0631\u06a9\u0632 \u062e\u0648\u0627\u0647\u06cc\u0645 \u067e\u0631\u062f\u0627\u062e\u062a \u0631\u0648\u06cc PyPDF2 \u0648 PyMuPDF \u0648 \u0631\u0648\u0634 \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u0645\u062a\u0646 \u0648 \u062a\u0635\u0627\u0648\u06cc\u0631 \u0631\u0627 \u0628\u0647 \u0633\u0627\u062f\u0647 \u062a\u0631\u06cc\u0646 \u0634\u06a9\u0644 \u0645\u0645\u06a9\u0646 \u062a\u0648\u0636\u06cc\u062d \u062f\u0647\u06cc\u062f.  \u0628\u0647 \u0645\u0646\u0638\u0648\u0631 \u062f\u0631\u06a9 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 PyPDF2\u060c \u062a\u0631\u06a9\u06cc\u0628\u06cc \u0627\u0632 \u0627\u0633\u0646\u0627\u062f \u0631\u0633\u0645\u06cc \u0648 \u0646\u0645\u0648\u0646\u0647 \u0647\u0627\u06cc \u0632\u06cc\u0627\u062f\u06cc \u06a9\u0647 \u0627\u0632 \u0645\u0646\u0627\u0628\u0639 \u062f\u06cc\u06af\u0631 \u062f\u0631 \u062f\u0633\u062a\u0631\u0633 \u0647\u0633\u062a\u0646\u062f\u060c \u06a9\u0645\u06a9 \u0645\u06cc \u06a9\u0646\u062f.  \u062f\u0631 \u0645\u0642\u0627\u0628\u0644\u060c \u0627\u0633\u0646\u0627\u062f \u0631\u0633\u0645\u06cc PyMuPDF \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0628\u0633\u06cc\u0627\u0631 \u0648\u0627\u0636\u062d \u062a\u0631 \u0648 \u0628\u0647 \u0637\u0648\u0631 \u0642\u0627\u0628\u0644 \u062a\u0648\u062c\u0647\u06cc \u0633\u0631\u06cc\u0639\u062a\u0631 \u0627\u0633\u062a.<\/p>\n<p>PyPDF2 \u0631\u0627 \u0645\u06cc \u062a\u0648\u0627\u0646 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u06cc\u06a9 \u0628\u0633\u062a\u0647 \u0646\u0631\u0645 \u0627\u0641\u0632\u0627\u0631\u06cc \u0645\u0639\u0645\u0648\u0644\u06cc \u06cc\u0627 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0622\u0646 \u0646\u0635\u0628 \u06a9\u0631\u062f <code>pip3<\/code> (\u0628\u0631\u0627\u06cc Python3).  \u062a\u0633\u062a \u0647\u0627\u06cc \u0627\u06cc\u0646\u062c\u0627 \u0628\u0631 \u0627\u0633\u0627\u0633 \u0631\u0648\u06cc \u0628\u0633\u062a\u0647 \u0628\u0631\u0627\u06cc \u062f\u0628\u06cc\u0627\u0646 \u0622\u06cc\u0646\u062f\u0647 GNU\/\u0644\u06cc\u0646\u0648\u06a9\u0633 \u0646\u0633\u062e\u0647 10 &#8220;Buster&#8221;.  \u0646\u0627\u0645 \u0628\u0633\u062a\u0647 \u062f\u0628\u06cc\u0627\u0646 \u0627\u0633\u062a <code>python3-pypdf2<\/code>.<\/p>\n<p><em>\u0644\u06cc\u0633\u062a 1<\/em> \u0648\u0627\u0631\u062f \u0645\u06cc \u06a9\u0646\u062f <code>PdfFileReader<\/code> \u06a9\u0644\u0627\u0633\u060c \u0627\u0648\u0644  \u0633\u067e\u0633 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0627\u06cc\u0646 \u06a9\u0644\u0627\u0633\u060c \u0633\u0646\u062f \u0631\u0627 \u0628\u0627\u0632 \u0645\u06cc \u06a9\u0646\u062f \u0648 \u0627\u0637\u0644\u0627\u0639\u0627\u062a \u0633\u0646\u062f \u0631\u0627 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0622\u0646 \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u0645\u06cc \u06a9\u0646\u062f <code>getDocumentInfo()<\/code> \u0631\u0648\u0634\u060c \u062a\u0639\u062f\u0627\u062f \u0635\u0641\u062d\u0627\u062a \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0634\u062f\u0647 <code>getDocumentInfo()<\/code>\u060c \u0648 \u0645\u062d\u062a\u0648\u0627\u06cc \u0627\u0648\u0644 page.<\/p>\n<p>\u0644\u0637\u0641\u0627\u064b \u062a\u0648\u062c\u0647 \u062f\u0627\u0634\u062a\u0647 \u0628\u0627\u0634\u06cc\u062f \u06a9\u0647 PyPDF2 \u0634\u0645\u0627\u0631\u0634 \u0635\u0641\u062d\u0627\u062a \u0631\u0627 \u0628\u0627 0 \u0634\u0631\u0648\u0639 \u0645\u06cc \u06a9\u0646\u062f \u0648 \u0628\u0647 \u0647\u0645\u06cc\u0646 \u062f\u0644\u06cc\u0644 \u0627\u0633\u062a \u06a9\u0647 \u062a\u0645\u0627\u0633 \u06af\u0631\u0641\u062a\u0647 \u0645\u06cc \u0634\u0648\u062f <code>pdf.getPage(0)<\/code> \u0627\u0648\u0644\u06cc \u0631\u0627 \u0628\u0627\u0632\u06cc\u0627\u0628\u06cc \u0645\u06cc \u06a9\u0646\u062f page \u0627\u0632 \u0633\u0646\u062f  \u062f\u0631 \u0646\u0647\u0627\u06cc\u062a \u0627\u0637\u0644\u0627\u0639\u0627\u062a \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u0634\u062f\u0647 \u062f\u0631 \u0622\u0646 \u0686\u0627\u067e \u0645\u06cc \u0634\u0648\u062f <code>stdout<\/code>.<\/p>\n<p><em>\u0641\u0647\u0631\u0633\u062a 1: \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u0627\u0637\u0644\u0627\u0639\u0627\u062a \u0648 \u0645\u062d\u062a\u0648\u0627\u06cc \u0633\u0646\u062f.<\/em><\/p>\n<pre><code class=\"hljs\">\n\n<span class=\"hljs-keyword\">from<\/span> PyPDF2 <span class=\"hljs-keyword\">import<\/span> PdfFileReader\n\npdf_document = <span class=\"hljs-string\">\"example.pdf\"<\/span>\n<span class=\"hljs-keyword\">with<\/span> <span class=\"hljs-built_in\">open<\/span>(pdf_document, <span class=\"hljs-string\">\"rb\"<\/span>) <span class=\"hljs-keyword\">as<\/span> filehandle:\n    pdf = PdfFileReader(filehandle)\n    info = pdf.getDocumentInfo()\n    pages = pdf.getNumPages()\n\n    <span class=\"hljs-built_in\">print<\/span> (info)\n    <span class=\"hljs-built_in\">print<\/span> (<span class=\"hljs-string\">\"number of pages: %i\"<\/span> % pages)\n\n    page1 = pdf.getPage(<span class=\"hljs-number\">0<\/span>)\n    <span class=\"hljs-built_in\">print<\/span>(page1)\n    <span class=\"hljs-built_in\">print<\/span>(page1.extractText())\n<\/code><\/pre>\n<p><img decoding=\"async\" class=\"img-responsive\" src=\"https:\/\/rasanegar.com\/blog\/wp-content\/uploads\/2024\/01\/working-with-pdfs-python-reading-splitting-1.png\" alt=\"\u0634\u06a9\u0644 1: \u0645\u062a\u0646 \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u0634\u062f\u0647 \u0627\u0632 \u06cc\u06a9 \u0641\u0627\u06cc\u0644 PDF \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 PyPDF2\" title=\"\"><br \/>\n<small>\u0634\u06a9\u0644 1: \u0645\u062a\u0646 \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u0634\u062f\u0647 \u0627\u0632 \u06cc\u06a9 \u0641\u0627\u06cc\u0644 PDF \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 PyPDF2<\/small><\/p>\n<p>\u0647\u0645\u0627\u0646\u0637\u0648\u0631 \u06a9\u0647 \u062f\u0631 \u0646\u0634\u0627\u0646 \u062f\u0627\u062f\u0647 \u0634\u062f\u0647 \u0627\u0633\u062a <em>\u0634\u06a9\u0644 1<\/em> \u062f\u0631 \u0628\u0627\u0644\u0627\u060c \u0645\u062a\u0646 \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u0634\u062f\u0647 \u0686\u0627\u067e \u0634\u062f\u0647 \u0627\u0633\u062a \u0631\u0648\u06cc \u06cc\u06a9 \u0645\u0628\u0646\u0627\u06cc \u0645\u0633\u062a\u0645\u0631  \u0647\u06cc\u0686 \u067e\u0627\u0631\u0627\u06af\u0631\u0627\u0641 \u06cc\u0627 \u062c\u062f\u0627\u0633\u0627\u0632\u06cc \u062c\u0645\u0644\u0647 \u0627\u06cc \u0648\u062c\u0648\u062f \u0646\u062f\u0627\u0631\u062f.  \u0647\u0645\u0627\u0646\u0637\u0648\u0631 \u06a9\u0647 \u062f\u0631 \u0645\u0633\u062a\u0646\u062f\u0627\u062a PyPDF2 \u0628\u06cc\u0627\u0646 \u0634\u062f\u060c \u062a\u0645\u0627\u0645 \u062f\u0627\u062f\u0647 \u0647\u0627\u06cc \u0645\u062a\u0646\u06cc \u0628\u0647 \u062a\u0631\u062a\u06cc\u0628\u06cc \u06a9\u0647 \u062f\u0631 \u062c\u0631\u06cc\u0627\u0646 \u0645\u062d\u062a\u0648\u0627\u06cc\u06cc \u0627\u0631\u0627\u0626\u0647 \u0634\u062f\u0647 \u0627\u0646\u062f\u060c \u0628\u0627\u0632\u06af\u0631\u062f\u0627\u0646\u062f\u0647 \u0645\u06cc \u0634\u0648\u0646\u062f. page\u060c \u0648 \u0628\u0627 \u062a\u06a9\u06cc\u0647 \u0631\u0648\u06cc \u0645\u0645\u06a9\u0646 \u0627\u0633\u062a \u0628\u0647 \u0628\u0631\u062e\u06cc \u0634\u06af\u0641\u062a\u06cc \u0647\u0627 \u0645\u0646\u062c\u0631 \u0634\u0648\u062f.  \u0627\u06cc\u0646 \u0639\u0645\u062f\u062a\u0627 \u0628\u0633\u062a\u06af\u06cc \u062f\u0627\u0631\u062f \u0631\u0648\u06cc \u0633\u0627\u062e\u062a\u0627\u0631 \u062f\u0627\u062e\u0644\u06cc \u0633\u0646\u062f PDF \u0648 \u0631\u0648\u0634 \u062a\u0648\u0644\u06cc\u062f \u062c\u0631\u06cc\u0627\u0646 \u062f\u0633\u062a\u0648\u0631\u0627\u0644\u0639\u0645\u0644 \u0647\u0627\u06cc PDF \u062a\u0648\u0633\u0637 PDF writer process.<\/p>\n<p>PyMuPDF \u0627\u0632 \u0648\u0628 \u0633\u0627\u06cc\u062a PyPi \u062f\u0631 \u062f\u0633\u062a\u0631\u0633 \u0627\u0633\u062a \u0648 \u0634\u0645\u0627 \u0628\u0633\u062a\u0647 \u0631\u0627 \u0628\u0627 \u062f\u0633\u062a\u0648\u0631 \u0632\u06cc\u0631 \u062f\u0631 a \u0646\u0635\u0628 \u0645\u06cc \u06a9\u0646\u06cc\u062f terminal:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-meta\">$<\/span><span class=\"bash\"> pip3 install PyMuPDF<\/span>\n<\/code><\/pre>\n<p>\u0646\u0645\u0627\u06cc\u0634 \u0627\u0637\u0644\u0627\u0639\u0627\u062a \u0633\u0646\u062f\u060c \u0686\u0627\u067e \u062a\u0639\u062f\u0627\u062f \u0635\u0641\u062d\u0627\u062a \u0648 \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u0645\u062a\u0646 \u06cc\u06a9 \u0633\u0646\u062f PDF \u0628\u0647 \u0631\u0648\u0634\u06cc \u0645\u0634\u0627\u0628\u0647 PyPDF2 \u0627\u0646\u062c\u0627\u0645 \u0645\u06cc \u0634\u0648\u062f (\u0646\u06af\u0627\u0647 \u06a9\u0646\u06cc\u062f \u0628\u0647 <em>\u0644\u06cc\u0633\u062a 2<\/em>).  \u0645\u0627\u0698\u0648\u0644\u06cc \u06a9\u0647 \u0642\u0631\u0627\u0631 \u0627\u0633\u062a \u0648\u0627\u0631\u062f \u0634\u0648\u062f \u0646\u0627\u0645\u06af\u0630\u0627\u0631\u06cc \u0634\u062f\u0647 \u0627\u0633\u062a <code>fitz<\/code>\u060c \u0648 \u0628\u0647 \u0646\u0627\u0645 \u0642\u0628\u0644\u06cc PyMuPDF \u0628\u0631\u0645\u06cc \u06af\u0631\u062f\u062f.<\/p>\n<p><em>\u0641\u0647\u0631\u0633\u062a 2: \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u0645\u062d\u062a\u0648\u0627 \u0627\u0632 \u06cc\u06a9 \u0633\u0646\u062f PDF \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 PyMuPDF.<\/em><\/p>\n<pre><code class=\"hljs\">\n\n<span class=\"hljs-keyword\">import<\/span> fitz\n\npdf_document = <span class=\"hljs-string\">\"example.pdf\"<\/span>\ndoc = fitz.<span class=\"hljs-built_in\">open<\/span>(pdf_document):\n<span class=\"hljs-built_in\">print<\/span> (<span class=\"hljs-string\">\"number of pages: %i\"<\/span> % doc.pageCount)\n<span class=\"hljs-built_in\">print<\/span>(doc.metadata)\n\npage1 = doc.loadPage(<span class=\"hljs-number\">0<\/span>)\npage1text = page1.getText(<span class=\"hljs-string\">\"text\"<\/span>)\n<span class=\"hljs-built_in\">print<\/span>(page1text)\n<\/code><\/pre>\n<p>\u0646\u06a9\u062a\u0647 \u062e\u0648\u0628 \u062f\u0631 \u0645\u0648\u0631\u062f PyMuPDF \u0627\u06cc\u0646 \u0627\u0633\u062a \u06a9\u0647 \u0633\u0627\u062e\u062a\u0627\u0631 \u0633\u0646\u062f \u0627\u0635\u0644\u06cc \u0631\u0627 \u062f\u0633\u062a \u0646\u062e\u0648\u0631\u062f\u0647 \u0646\u06af\u0647 \u0645\u06cc\u200c\u062f\u0627\u0631\u062f &#8211; \u06a9\u0644 \u067e\u0627\u0631\u0627\u06af\u0631\u0627\u0641\u200c\u0647\u0627 \u0628\u0627 \u0634\u06a9\u0633\u062a \u062e\u0637 \u0647\u0645\u0627\u0646\u0637\u0648\u0631 \u06a9\u0647 \u062f\u0631 \u0633\u0646\u062f PDF \u0647\u0633\u062a\u0646\u062f \u062d\u0641\u0638 \u0645\u06cc\u200c\u0634\u0648\u0646\u062f (\u0646\u06af\u0627\u0647 \u06a9\u0646\u06cc\u062f \u0628\u0647 <em>\u0634\u06a9\u0644 2<\/em>).<\/p>\n<p><img decoding=\"async\" class=\"img-responsive\" src=\"https:\/\/rasanegar.com\/blog\/wp-content\/uploads\/2024\/01\/working-with-pdfs-python-reading-splitting-2.png\" alt=\"\u0634\u06a9\u0644 2: \u062f\u0627\u062f\u0647 \u0647\u0627\u06cc \u0645\u062a\u0646\u06cc \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u0634\u062f\u0647\" title=\"\"><br \/>\n<small>\u0634\u06a9\u0644 2: \u062f\u0627\u062f\u0647 \u0647\u0627\u06cc \u0645\u062a\u0646\u06cc \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u0634\u062f\u0647<\/small><\/p>\n<p>PyMuPDF \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u062a\u0635\u0627\u0648\u06cc\u0631 \u0627\u0632 \u0627\u0633\u0646\u0627\u062f PDF \u0631\u0627 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0627\u06cc\u0646 \u0631\u0648\u0634 \u0633\u0627\u062f\u0647 \u0645\u06cc \u06a9\u0646\u062f <code>getPageImageList()<\/code>. <em>\u0644\u06cc\u0633\u062a 3<\/em> \u0628\u0631 \u0627\u0633\u0627\u0633 \u0631\u0648\u06cc \u0646\u0645\u0648\u0646\u0647 \u0627\u06cc \u0627\u0632 \u0648\u06cc\u06a9\u06cc PyMuPDF page\u060c \u0648 \u062a\u0645\u0627\u0645 \u062a\u0635\u0627\u0648\u06cc\u0631 \u0631\u0627 \u0627\u0632 PDF \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0641\u0627\u06cc\u0644 PNG \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u0648 \u0630\u062e\u06cc\u0631\u0647 \u0645\u06cc \u06a9\u0646\u062f \u0631\u0648\u06cc \u0622 page-\u062a\u0648\u0633\u0637-page \u0627\u0633\u0627\u0633  \u0627\u06af\u0631 \u062a\u0635\u0648\u06cc\u0631\u06cc \u062f\u0627\u0631\u0627\u06cc \u0641\u0636\u0627\u06cc \u0631\u0646\u06af\u06cc CMYK \u0628\u0627\u0634\u062f\u060c \u0627\u0628\u062a\u062f\u0627 \u0628\u0647 RGB \u062a\u0628\u062f\u06cc\u0644 \u0645\u06cc \u0634\u0648\u062f.<\/p>\n<p><em>\u0641\u0647\u0631\u0633\u062a 3: \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u062a\u0635\u0627\u0648\u06cc\u0631.<\/em><\/p>\n<pre><code class=\"hljs\">\n\n<span class=\"hljs-keyword\">import<\/span> fitz\n\npdf_document = fitz.<span class=\"hljs-built_in\">open<\/span>(<span class=\"hljs-string\">\"file.pdf\"<\/span>)\n<span class=\"hljs-keyword\">for<\/span> current_page <span class=\"hljs-keyword\">in<\/span> <span class=\"hljs-built_in\">range<\/span>(<span class=\"hljs-built_in\">len<\/span>(pdf_document)):\n    <span class=\"hljs-keyword\">for<\/span> image <span class=\"hljs-keyword\">in<\/span> pdf_document.getPageImageList(current_page):\n        xref = image(<span class=\"hljs-number\">0<\/span>)\n        pix = fitz.Pixmap(pdf_document, xref)\n        <span class=\"hljs-keyword\">if<\/span> pix.n &lt; <span class=\"hljs-number\">5<\/span>:        \n            pix.writePNG(<span class=\"hljs-string\">\"page%s-%s.png\"<\/span> % (current_page, xref))\n        <span class=\"hljs-keyword\">else<\/span>:                \n            pix1 = fitz.Pixmap(fitz.csRGB, pix)\n            pix1.writePNG(<span class=\"hljs-string\">\"page%s-%s.png\"<\/span> % (current_page, xref))\n            pix1 = <span class=\"hljs-literal\">None<\/span>\n        pix = <span class=\"hljs-literal\">None<\/span>\n<\/code><\/pre>\n<p>\u0627\u062c\u0631\u0627\u06cc \u0627\u06cc\u0646 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u067e\u0627\u06cc\u062a\u0648\u0646 \u0631\u0648\u06cc \u06cc\u06a9 400 page PDF\u060c 117 \u062a\u0635\u0648\u06cc\u0631 \u0631\u0627 \u062f\u0631 \u06a9\u0645\u062a\u0631 \u0627\u0632 3 \u062b\u0627\u0646\u06cc\u0647 \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u06a9\u0631\u062f \u06a9\u0647 \u0628\u0633\u06cc\u0627\u0631 \u0634\u06af\u0641\u062a \u0627\u0646\u06af\u06cc\u0632 \u0627\u0633\u062a.  \u062a\u0635\u0627\u0648\u06cc\u0631 \u062c\u062f\u0627\u06af\u0627\u0646\u0647 \u062f\u0631 \u0641\u0631\u0645\u062a PNG \u0630\u062e\u06cc\u0631\u0647 \u0645\u06cc \u0634\u0648\u0646\u062f.  \u0628\u0631\u0627\u06cc \u062d\u0641\u0638 \u0641\u0631\u0645\u062a \u0648 \u0627\u0646\u062f\u0627\u0632\u0647 \u062a\u0635\u0648\u06cc\u0631 \u0627\u0635\u0644\u06cc\u060c \u0628\u0647 \u062c\u0627\u06cc \u062a\u0628\u062f\u06cc\u0644 \u0628\u0647 PNG\u060c \u0646\u06af\u0627\u0647\u06cc \u0628\u0647 \u0646\u0633\u062e\u0647 \u0647\u0627\u06cc \u062a\u0648\u0633\u0639\u0647 \u06cc\u0627\u0641\u062a\u0647 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0647\u0627 \u062f\u0631 <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/github.com\/pymupdf\/PyMuPDF\/wiki\">\u0648\u06cc\u06a9\u06cc PyMuPDF<\/a>.<\/p>\n<p><img decoding=\"async\" class=\"img-responsive\" src=\"https:\/\/rasanegar.com\/blog\/wp-content\/uploads\/2024\/01\/working-with-pdfs-python-reading-splitting-3.png\" alt=\"\u0634\u06a9\u0644 3: \u062a\u0635\u0627\u0648\u06cc\u0631 \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u0634\u062f\u0647\" title=\"\"><br \/>\n<small>\u0634\u06a9\u0644 3: \u062a\u0635\u0627\u0648\u06cc\u0631 \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u0634\u062f\u0647<\/small><\/p>\n<h2 id=\"splittingpdfsintopageswithpypdf2\"><span class=\"ez-toc-section\" id=\"%d8%aa%d9%82%d8%b3%db%8c%d9%85_pdf_%d8%a8%d9%87_%d8%b5%d9%81%d8%ad%d8%a7%d8%aa_%d8%a8%d8%a7_pypdf2\"><\/span>\u062a\u0642\u0633\u06cc\u0645 PDF \u0628\u0647 \u0635\u0641\u062d\u0627\u062a \u0628\u0627 PyPDF2<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>\u0628\u0631\u0627\u06cc \u0627\u06cc\u0646 \u0645\u062b\u0627\u0644\u060c \u0647\u0631 \u062f\u0648 <code>PdfFileReader<\/code> \u0648 <code>PdfFileWriter<\/code> \u06a9\u0644\u0627\u0633 \u0647\u0627 \u0627\u0628\u062a\u062f\u0627 \u0628\u0627\u06cc\u062f \u0648\u0627\u0631\u062f \u0634\u0648\u0646\u062f.  \u0633\u067e\u0633 \u0641\u0627\u06cc\u0644 PDF \u0631\u0627 \u0628\u0627\u0632 \u0645\u06cc \u06a9\u0646\u06cc\u0645\u060c \u06cc\u06a9 \u0634\u06cc \u062e\u0648\u0627\u0646\u0646\u062f\u0647 \u0627\u06cc\u062c\u0627\u062f \u0645\u06cc \u06a9\u0646\u06cc\u0645 \u0648 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0634\u06cc Reader \u0631\u0648\u06cc \u062a\u0645\u0627\u0645 \u0635\u0641\u062d\u0627\u062a \u062d\u0644\u0642\u0647 \u0645\u06cc \u0632\u0646\u06cc\u0645. <code>getNumPages<\/code> \u0631\u0648\u0634.<\/p>\n<p>\u062f\u0627\u062e\u0644 \u0627\u0632 <code>for<\/code> \u062d\u0644\u0642\u0647\u060c \u0645\u0627 \u06cc\u06a9 \u0646\u0645\u0648\u0646\u0647 \u062c\u062f\u06cc\u062f \u0627\u0632 <code>PdfFileWriter<\/code>\u060c \u06a9\u0647 \u0647\u0646\u0648\u0632 \u0647\u06cc\u0686 \u0635\u0641\u062d\u0647 \u0627\u06cc \u0646\u062f\u0627\u0631\u062f.  \u0633\u067e\u0633 \u062c\u0631\u06cc\u0627\u0646 \u0631\u0627 \u0627\u0636\u0627\u0641\u0647 \u0645\u06cc \u06a9\u0646\u06cc\u0645 page \u0628\u0647 \u0634\u06cc \u0646\u0648\u06cc\u0633\u0646\u062f\u0647 \u0645\u0627 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 <code>pdfWriter.addPage()<\/code> \u0631\u0648\u0634.  \u0627\u06cc\u0646 \u0631\u0648\u0634 \u0627\u0644\u0641 \u0631\u0627 \u0645\u06cc \u067e\u0630\u06cc\u0631\u062f page \u0634\u06cc\u060c \u06a9\u0647 \u0645\u0627 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 <code>PdfFileReader.getPage()<\/code> \u0631\u0648\u0634.<\/p>\n<p>\u0645\u0631\u062d\u0644\u0647 \u0628\u0639\u062f\u06cc \u0627\u06cc\u062c\u0627\u062f \u06cc\u06a9 \u0646\u0627\u0645 \u0641\u0627\u06cc\u0644 \u0645\u0646\u062d\u0635\u0631 \u0628\u0647 \u0641\u0631\u062f \u0627\u0633\u062a \u06a9\u0647 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0646\u0627\u0645 \u0627\u0635\u0644\u06cc \u0641\u0627\u06cc\u0644 \u0628\u0647 \u0627\u0636\u0627\u0641\u0647 \u06a9\u0644\u0645\u0647 &#8220;&#8221; \u0627\u06cc\u0646 \u06a9\u0627\u0631 \u0631\u0627 \u0627\u0646\u062c\u0627\u0645 \u0645\u06cc \u062f\u0647\u06cc\u0645.page&#8221;\u060c \u0628\u0647 \u0639\u0644\u0627\u0648\u0647 page \u0639\u062f\u062f.  1 \u0631\u0627 \u0628\u0647 \u062c\u0631\u06cc\u0627\u0646 \u0627\u0636\u0627\u0641\u0647 \u0645\u06cc \u06a9\u0646\u06cc\u0645 page \u0639\u062f\u062f \u0632\u06cc\u0631\u0627 PyPDF2 \u0639\u062f\u062f \u0631\u0627 \u0645\u06cc \u0634\u0645\u0627\u0631\u062f page \u0627\u0639\u062f\u0627\u062f\u06cc \u06a9\u0647 \u0627\u0632 \u0635\u0641\u0631 \u0634\u0631\u0648\u0639 \u0645\u06cc \u0634\u0648\u0646\u062f<\/p>\n<p>\u062f\u0631 \u0646\u0647\u0627\u06cc\u062a\u060c \u0646\u0627\u0645 \u0641\u0627\u06cc\u0644 \u062c\u062f\u06cc\u062f \u0631\u0627 \u062f\u0631 \u062d\u0627\u0644\u062a \u00ab\u0646\u0648\u0634\u062a\u0646 \u0628\u0627\u06cc\u0646\u0631\u06cc\u00bb \u0628\u0627\u0632 \u0645\u06cc\u200c\u06a9\u0646\u06cc\u0645 (\u062d\u0627\u0644\u062a <code>wb<\/code>) \u0648 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0646\u06cc\u062f <code>write()<\/code> \u0631\u0648\u0634 \u0627\u0632 <code>pdfWriter<\/code> \u06a9\u0644\u0627\u0633 \u0628\u0631\u0627\u06cc \u0630\u062e\u06cc\u0631\u0647 \u0645\u0648\u0627\u0631\u062f \u0627\u0633\u062a\u062e\u0631\u0627\u062c \u0634\u062f\u0647 page \u0628\u0647 \u062f\u06cc\u0633\u06a9<\/p>\n<p><em>\u0641\u0647\u0631\u0633\u062a 4: \u062a\u0642\u0633\u06cc\u0645 \u06cc\u06a9 PDF \u0628\u0647 \u0635\u0641\u062d\u0627\u062a \u062a\u06a9.<\/em><\/p>\n<pre><code class=\"hljs\">\n\n<span class=\"hljs-keyword\">from<\/span> PyPDF2 <span class=\"hljs-keyword\">import<\/span> PdfFileReader, PdfFileWriter\n\npdf_document = <span class=\"hljs-string\">\"example.pdf\"<\/span>\npdf = PdfFileReader(pdf_document)\n\n<span class=\"hljs-keyword\">for<\/span> page <span class=\"hljs-keyword\">in<\/span> <span class=\"hljs-built_in\">range<\/span>(pdf.getNumPages()):\n    pdf_writer = PdfFileWriter\n    current_page = pdf.getPage(page)\n    pdf_writer.addPage(current_page)\n\n    outputFilename = <span class=\"hljs-string\">\"example-page-{}.pdf\"<\/span>.<span class=\"hljs-built_in\">format<\/span>(page + <span class=\"hljs-number\">1<\/span>)\n    <span class=\"hljs-keyword\">with<\/span> <span class=\"hljs-built_in\">open<\/span>(outputFilename, <span class=\"hljs-string\">\"wb\"<\/span>) <span class=\"hljs-keyword\">as<\/span> out:\n        pdf_writer.write(out)\n\n        <span class=\"hljs-built_in\">print<\/span>(<span class=\"hljs-string\">\"created\"<\/span>, outputFilename)\n<\/code><\/pre>\n<p><img decoding=\"async\" class=\"img-responsive\" src=\"https:\/\/rasanegar.com\/blog\/wp-content\/uploads\/2024\/01\/working-with-pdfs-python-reading-splitting-4.png\" alt=\"\u0634\u06a9\u0644 4: \u062a\u0642\u0633\u06cc\u0645 \u06cc\u06a9 PDF\" title=\"\"><br \/>\n<small>\u0634\u06a9\u0644 4: \u062a\u0642\u0633\u06cc\u0645 \u06cc\u06a9 PDF<\/small><\/p>\n<h2 id=\"findallpagescontainingtext\"><span class=\"ez-toc-section\" id=\"%d9%87%d9%85%d9%87_%d8%b5%d9%81%d8%ad%d8%a7%d8%aa_%d8%ad%d8%a7%d9%88%db%8c_%d9%85%d8%aa%d9%86_%d8%b1%d8%a7_%d9%be%db%8c%d8%af%d8%a7_%da%a9%d9%86%db%8c%d8%af\"><\/span>\u0647\u0645\u0647 \u0635\u0641\u062d\u0627\u062a \u062d\u0627\u0648\u06cc \u0645\u062a\u0646 \u0631\u0627 \u067e\u06cc\u062f\u0627 \u06a9\u0646\u06cc\u062f<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>\u0627\u06cc\u0646 \u0645\u0648\u0631\u062f \u06a9\u0627\u0645\u0644\u0627\u064b \u06a9\u0627\u0631\u0628\u0631\u062f\u06cc \u0627\u0633\u062a \u0648 \u0645\u0634\u0627\u0628\u0647 \u0622\u0646 \u0639\u0645\u0644 \u0645\u06cc \u06a9\u0646\u062f <code>pdfgrep<\/code>.  \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 PyMuPDF\u060c \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u062a\u0645\u0627\u0645 \u0645\u0648\u0627\u0631\u062f \u0631\u0627 \u0628\u0631\u0645\u06cc \u06af\u0631\u062f\u0627\u0646\u062f page \u0627\u0639\u062f\u0627\u062f\u06cc \u06a9\u0647 \u0634\u0627\u0645\u0644 \u0631\u0634\u062a\u0647 \u062c\u0633\u062a\u062c\u0648\u06cc \u062f\u0627\u062f\u0647 \u0634\u062f\u0647 \u0647\u0633\u062a\u0646\u062f.  \u0635\u0641\u062d\u0627\u062a \u06cc\u06a9\u06cc \u067e\u0633 \u0627\u0632 \u062f\u06cc\u06af\u0631\u06cc \u0648 \u0628\u0627 \u06a9\u0645\u06a9 <code>searchFor()<\/code> \u0631\u0648\u0634 \u062a\u0645\u0627\u0645 \u0631\u062e\u062f\u0627\u062f\u0647\u0627\u06cc \u0631\u0634\u062a\u0647 \u062c\u0633\u062a\u062c\u0648 \u0634\u0646\u0627\u0633\u0627\u06cc\u06cc \u0645\u06cc \u0634\u0648\u0646\u062f.  \u062f\u0631 \u0635\u0648\u0631\u062a \u062a\u0637\u0627\u0628\u0642 \u06cc\u06a9 \u067e\u06cc\u0627\u0645 \u0645\u0637\u0627\u0628\u0642 \u0686\u0627\u067e \u0645\u06cc \u0634\u0648\u062f \u0631\u0648\u06cc <code>stdout<\/code>.<\/p>\n<p><em>\u0641\u0647\u0631\u0633\u062a 5: \u06cc\u06a9 \u0645\u062a\u0646 \u062f\u0627\u062f\u0647 \u0634\u062f\u0647 \u0631\u0627 \u062c\u0633\u062a\u062c\u0648 \u06a9\u0646\u06cc\u062f.<\/em><\/p>\n<pre><code class=\"hljs\">\n\n<span class=\"hljs-keyword\">import<\/span> fitz\n\nfilename = <span class=\"hljs-string\">\"example.pdf\"<\/span>\nsearch_term = <span class=\"hljs-string\">\"invoice\"<\/span>\npdf_document = fitz.<span class=\"hljs-built_in\">open<\/span>(filename):\n\n<span class=\"hljs-keyword\">for<\/span> current_page <span class=\"hljs-keyword\">in<\/span> <span class=\"hljs-built_in\">range<\/span>(<span class=\"hljs-built_in\">len<\/span>(pdf_document)):\n    page = pdf_document.loadPage(current_page)\n    <span class=\"hljs-keyword\">if<\/span> page.searchFor(search_term):\n        <span class=\"hljs-built_in\">print<\/span>(<span class=\"hljs-string\">\"%s found \u0631\u0648\u06cc page %i\"<\/span> % (search_term, current_page))\n<\/code><\/pre>\n<p><em>\u0634\u06a9\u0644 5<\/em> \u062f\u0631 \u0632\u06cc\u0631 \u0646\u062a\u06cc\u062c\u0647 \u062c\u0633\u062a\u062c\u0648\u06cc \u0639\u0628\u0627\u0631\u062a &#8220;Debian&#8221; \u0631\u0627 \u0646\u0634\u0627\u0646 \u0645\u06cc \u062f\u0647\u062f GNU\/Linux&#8221; \u062f\u0631 400-page \u06a9\u062a\u0627\u0628.<\/p>\n<p><img decoding=\"async\" class=\"img-responsive\" src=\"https:\/\/rasanegar.com\/blog\/wp-content\/uploads\/2024\/01\/working-with-pdfs-python-reading-splitting-5.png\" alt=\"\u0634\u06a9\u0644 5: \u062c\u0633\u062a\u062c\u0648\u06cc \u06cc\u06a9 \u0633\u0646\u062f PDF\" title=\"\"><br \/>\n<small>\u0634\u06a9\u0644 5: \u062c\u0633\u062a\u062c\u0648\u06cc \u06cc\u06a9 \u0633\u0646\u062f PDF<\/small><\/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>\u0631\u0648\u0634 \u0647\u0627\u06cc \u0646\u0634\u0627\u0646 \u062f\u0627\u062f\u0647 \u0634\u062f\u0647 \u062f\u0631 \u0627\u06cc\u0646\u062c\u0627 \u0628\u0633\u06cc\u0627\u0631 \u0642\u062f\u0631\u062a\u0645\u0646\u062f \u0647\u0633\u062a\u0646\u062f.  \u0628\u0627 \u062a\u0639\u062f\u0627\u062f \u0646\u0633\u0628\u062a\u0627\u064b \u06a9\u0645\u06cc \u0627\u0632 \u062e\u0637\u0648\u0637 \u06a9\u062f\u060c \u0646\u062a\u06cc\u062c\u0647 \u0628\u0647 \u0631\u0627\u062d\u062a\u06cc \u0628\u062f\u0633\u062a \u0645\u06cc \u0622\u06cc\u062f.  \u0645\u0648\u0627\u0631\u062f \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0628\u06cc\u0634\u062a\u0631 \u062f\u0631 \u0642\u0633\u0645\u062a \u062f\u0648\u0645 (\u0628\u0647 \u0632\u0648\u062f\u06cc!) \u0645\u0648\u0631\u062f \u0628\u0631\u0631\u0633\u06cc \u0642\u0631\u0627\u0631 \u0645\u06cc \u06af\u06cc\u0631\u0646\u062f \u06a9\u0647 \u0634\u0627\u0645\u0644 \u0627\u0641\u0632\u0648\u062f\u0646 \u0648\u0627\u062a\u0631\u0645\u0627\u0631\u06a9 \u0628\u0647 PDF \u0645\u06cc \u0634\u0648\u062f.<\/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 1403-01-23 13:42:04<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;16321&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;\u06a9\u0627\u0631 \u0628\u0627 PDF \u062f\u0631 \u067e\u0627\u06cc\u062a\u0648\u0646: \u062e\u0648\u0627\u0646\u062f\u0646 \u0648 \u062a\u0642\u0633\u06cc\u0645 \u0635\u0641\u062d\u0627\u062a&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>\u0627\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647 \u0627\u0648\u0644\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647 \u0627\u0632 \u0645\u062c\u0645\u0648\u0639\u0647 \u0627\u0633\u062a \u0631\u0648\u06cc \u06a9\u0627\u0631 \u0628\u0627 PDF \u062f\u0631 \u067e\u0627\u06cc\u062a\u0648\u0646: \u0641\u0631\u0645\u062a \u0633\u0646\u062f PDF \u0627\u0645\u0631\u0648\u0632\u0647\u060c \u0641\u0631\u0645\u062a \u0633\u0646\u062f \u0642\u0627\u0628\u0644 \u062d\u0645\u0644 (PDF) \u0628\u0647 \u0631\u0627\u06cc\u062c \u062a\u0631\u06cc\u0646 \u0641\u0631\u0645\u062a \u0647\u0627\u06cc \u062f\u0627\u062f\u0647 \u062a\u0639\u0644\u0642 \u062f\u0627\u0631\u062f. \u062f\u0631 \u0633\u0627\u0644 1990\u060c \u0633\u0627\u062e\u062a\u0627\u0631 \u06cc\u06a9 \u0633\u0646\u062f PDF \u062a\u0648\u0633\u0637 Adobe \u062a\u0639\u0631\u06cc\u0641 \u0634\u062f. \u0627\u06cc\u062f\u0647 \u067e\u0634\u062a \u0641\u0631\u0645\u062a PDF \u0627\u06cc\u0646 \u0627\u0633\u062a \u06a9\u0647 \u062f\u0627\u062f\u0647 \u0647\u0627 \/ \u0627\u0633\u0646\u0627\u062f \u0627\u0631\u0633\u0627\u0644 \u0634\u062f\u0647 \u0628\u0631\u0627\u06cc [&hellip;]<\/p>\n","protected":false},"author":3,"featured_media":16322,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1743,620],"tags":[],"class_list":["post-16321","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\/16321","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=16321"}],"version-history":[{"count":0,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/posts\/16321\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/media\/16322"}],"wp:attachment":[{"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/media?parent=16321"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/categories?post=16321"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/tags?post=16321"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}