{"_id":"pdf-to-text","_rev":"22-3ec2a175077593e9484c34aba682c0bd","name":"pdf-to-text","description":"Extract the text from pdf files","dist-tags":{"latest":"0.0.7"},"versions":{"0.0.0":{"name":"pdf-to-text","version":"0.0.0","description":"Extract the text from pdf files","main":"index.js","directories":{"test":"test"},"scripts":{"test":"mocha --reporter spec"},"repository":{"type":"git","url":"git@github.com:zetahernandez/pdf-to-text.git"},"keywords":["pdf","text","nodejs"],"author":{"name":"Fernando Hernandez"},"license":"ISC","bugs":{"url":"https://github.com/zetahernandez/pdf-to-text/issues"},"homepage":"https://github.com/zetahernandez/pdf-to-text","devDependencies":{"mocha":"~1.21.4","should":"~4.0.4"},"_id":"pdf-to-text@0.0.0","dist":{"shasum":"d6ae4de5dee54e77cc38a039ee898e2489f9b199","tarball":"https://registry.npmjs.org/pdf-to-text/-/pdf-to-text-0.0.0.tgz","integrity":"sha512-l0EDjkWR7bqE6706dgnCBOpfxnnnYdpf4Bq2pBAYHvoGJVgqq7Yd7h8/hltLJiidX05XC2kEYtKFSM7PiBM+JQ==","signatures":[{"keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA","sig":"MEYCIQCniZlPPF3aZqMajveOroVXe6rDDEGX/Stiob2Y8rX9SgIhANsLVn6hZKWD1uo/evEOAV1ylLaPF4V7zZc3xyRAgZFu"}]},"_from":".","_npmVersion":"1.3.24","_npmUser":{"name":"zetahernandez","email":"zetahernandez@gmail.com"},"maintainers":[{"name":"zetahernandez","email":"zetahernandez@gmail.com"}]},"0.0.1":{"name":"pdf-to-text","version":"0.0.1","description":"Extract the text from pdf files","main":"index.js","directories":{"test":"test"},"scripts":{"test":"mocha --reporter spec"},"repository":{"type":"git","url":"git@github.com:zetahernandez/pdf-to-text.git"},"keywords":["pdf","text","nodejs"],"author":{"name":"Fernando Hernandez"},"license":"ISC","bugs":{"url":"https://github.com/zetahernandez/pdf-to-text/issues"},"homepage":"https://github.com/zetahernandez/pdf-to-text","devDependencies":{"mocha":"~1.21.4","should":"~4.0.4"},"_id":"pdf-to-text@0.0.1","dist":{"shasum":"86061b69f20db2ef6587715b6f396c4e7ddc4280","tarball":"https://registry.npmjs.org/pdf-to-text/-/pdf-to-text-0.0.1.tgz","integrity":"sha512-awZrSReD90d+XXfX5PfkojrHKzQGo83A2CEuyQIMIq3ZyYVT/nbVw2cSU1OuMTnP2Mba4zLP4OBhRsTR+6+7DQ==","signatures":[{"keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA","sig":"MEYCIQDmlr0f9aklbuKb4UKscAymYLIJxSU6RNp40KBU2WAwRQIhAI+z/HWz1Ayv9sSxU2bcT1pkUd1KRwsDgmnVQhU0suHU"}]},"_from":".","_npmVersion":"1.3.24","_npmUser":{"name":"zetahernandez","email":"zetahernandez@gmail.com"},"maintainers":[{"name":"zetahernandez","email":"zetahernandez@gmail.com"}]},"0.0.2":{"name":"pdf-to-text","version":"0.0.2","description":"Extract the text from pdf files","main":"index.js","directories":{"test":"test"},"scripts":{"test":"mocha --reporter spec"},"repository":{"type":"git","url":"git@github.com:zetahernandez/pdf-to-text.git"},"keywords":["pdf","text","nodejs"],"author":{"name":"Fernando Hernandez"},"license":"ISC","bugs":{"url":"https://github.com/zetahernandez/pdf-to-text/issues"},"homepage":"https://github.com/zetahernandez/pdf-to-text","devDependencies":{"mocha":"~1.21.4","should":"~4.0.4"},"_id":"pdf-to-text@0.0.2","dist":{"shasum":"d995056797f01aff77b91ea733a7b6244c2ce6f4","tarball":"https://registry.npmjs.org/pdf-to-text/-/pdf-to-text-0.0.2.tgz","integrity":"sha512-GSmPXjcKX1+0DO3RSUJqoFi2in3g9gW/L6vnVi3xyvEpxuD1+aTjhd+0iJlkuNjw22vXa1ugbNVVEhrNOlOZJA==","signatures":[{"keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA","sig":"MEUCIQCKoMlBLxODTcIpOgfGo3ff7IrLXwJ9wy9Xv4HPnQZYhAIgXrDzsYbjgwx+w+wo0yKqYaMGi4Z0qOcmQff0a2uS7vg="}]},"_from":".","_npmVersion":"1.3.24","_npmUser":{"name":"zetahernandez","email":"zetahernandez@gmail.com"},"maintainers":[{"name":"zetahernandez","email":"zetahernandez@gmail.com"}]},"0.0.3":{"name":"pdf-to-text","version":"0.0.3","description":"Extract the text from pdf files","main":"index.js","directories":{"test":"test"},"scripts":{"test":"mocha --reporter spec"},"repository":{"type":"git","url":"git@github.com:zetahernandez/pdf-to-text.git"},"keywords":["pdf","text","nodejs"],"author":{"name":"Fernando Hernandez"},"license":"ISC","bugs":{"url":"https://github.com/zetahernandez/pdf-to-text/issues"},"homepage":"https://github.com/zetahernandez/pdf-to-text","devDependencies":{"mocha":"~1.21.4","should":"~4.0.4"},"_id":"pdf-to-text@0.0.3","dist":{"shasum":"586b63cb1546a39daa2d6f9df7f5fbeb3a2004c1","tarball":"https://registry.npmjs.org/pdf-to-text/-/pdf-to-text-0.0.3.tgz","integrity":"sha512-K3ztAmmzTWui1qZno8sarrHFGRv7gBSPTClUuiQ2qjzGPeGApfccd596X0PTNSawQACyTVuT3Pv+X4acxTp5mg==","signatures":[{"keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA","sig":"MEQCIAaA5urYRY5yoY3fZ01S6Afbtb2yuVsrQHwGgi1RDKzLAiA8hkdJ8hkKqjmGAxYc/ObFfUDP2ewULVEjm3exCV7POg=="}]},"_from":".","_npmVersion":"1.3.24","_npmUser":{"name":"zetahernandez","email":"zetahernandez@gmail.com"},"maintainers":[{"name":"zetahernandez","email":"zetahernandez@gmail.com"}]},"0.0.4":{"name":"pdf-to-text","version":"0.0.4","description":"Extract the text from pdf files","main":"index.js","directories":{"test":"test"},"scripts":{"test":"mocha --reporter spec"},"repository":{"type":"git","url":"git@github.com:zetahernandez/pdf-to-text.git"},"keywords":["pdf","text","nodejs"],"author":{"name":"Fernando Hernandez"},"license":"ISC","bugs":{"url":"https://github.com/zetahernandez/pdf-to-text/issues"},"homepage":"https://github.com/zetahernandez/pdf-to-text","devDependencies":{"mocha":"~1.21.4","should":"~4.0.4"},"_id":"pdf-to-text@0.0.4","dist":{"shasum":"40eecd0836a70e387254de804e4d744a25621656","tarball":"https://registry.npmjs.org/pdf-to-text/-/pdf-to-text-0.0.4.tgz","integrity":"sha512-83gTo5q4+iNslwdHwqfG0A3EyQnYgo7w8IAH7vOpE6Bfg8D3JkR04FlSUHi1/qOhKTloC9YXTR7evUrvThiN/g==","signatures":[{"keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA","sig":"MEQCICzWjyZa1eZz8CxjsA0ZHsj67fhw1qB/8A912jQ5EcquAiBNI6PZleZvvMm9F2Q6M1N/vVP0pglPTfgXoHsNXjPnBQ=="}]},"_from":".","_npmVersion":"1.3.24","_npmUser":{"name":"zetahernandez","email":"zetahernandez@gmail.com"},"maintainers":[{"name":"zetahernandez","email":"zetahernandez@gmail.com"}]},"0.0.5":{"name":"pdf-to-text","version":"0.0.5","description":"Extract the text from pdf files","main":"index.js","directories":{"test":"test"},"scripts":{"test":"mocha --reporter spec"},"repository":{"type":"git","url":"git@github.com:zetahernandez/pdf-to-text.git"},"keywords":["pdf","text","nodejs"],"author":{"name":"Fernando Hernandez"},"license":"ISC","bugs":{"url":"https://github.com/zetahernandez/pdf-to-text/issues"},"homepage":"https://github.com/zetahernandez/pdf-to-text","devDependencies":{"mocha":"~1.21.4","should":"~4.0.4"},"_id":"pdf-to-text@0.0.5","dist":{"shasum":"cfffa3193de5a14985a1ee469de8822c833815cc","tarball":"https://registry.npmjs.org/pdf-to-text/-/pdf-to-text-0.0.5.tgz","integrity":"sha512-Lf/K1BItrXrezbyWDRzRbhDNp3Zm7umo/hYb9ggNi1jHLx5d9gP5Yf+LXGON8lvYA1DsZORaOBV6CrMTncaZzg==","signatures":[{"keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA","sig":"MEUCIC30CrCs37B+4OO15j2nCSiChCfiiUKE0iJJVFeinrAYAiEAheAyhXGksrUvO31M3BLWFX2pN1KWT5ZfJosX5wzlC4A="}]},"_from":".","_npmVersion":"1.3.24","_npmUser":{"name":"zetahernandez","email":"zetahernandez@gmail.com"},"maintainers":[{"name":"zetahernandez","email":"zetahernandez@gmail.com"}]},"0.0.6":{"name":"pdf-to-text","version":"0.0.6","description":"Extract the text from pdf files","main":"index.js","directories":{"test":"test"},"scripts":{"test":"mocha --reporter spec"},"repository":{"type":"git","url":"git@github.com:zetahernandez/pdf-to-text.git"},"keywords":["pdf","text","extract","convert","parse","info","pdf-to-text","pdftotext","nodejs"],"author":{"name":"Fernando Hernandez"},"license":"ISC","bugs":{"url":"https://github.com/zetahernandez/pdf-to-text/issues"},"homepage":"https://github.com/zetahernandez/pdf-to-text","devDependencies":{"mocha":"~1.21.4","should":"~4.0.4"},"_id":"pdf-to-text@0.0.6","dist":{"shasum":"b5f40dafaa79cad12589d8a4f43ebe435dc69d53","tarball":"https://registry.npmjs.org/pdf-to-text/-/pdf-to-text-0.0.6.tgz","integrity":"sha512-fOsIgtDWCeseBtAc59KT1BPb/VbesDxbsStNaAuCOwVdNQbZKLCDJPmaNnYgwpzM8KhwH9F7y9Ae6435ziNU3A==","signatures":[{"keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA","sig":"MEQCICdctMBY38xo9kLmQpXQmFQlN5uVeE+gGL+cdbpdzG3CAiAUuH2CEJhVBjeY1dD6uR+7JoisunCxsCE556Y8MiC9ug=="}]},"_from":".","_npmVersion":"1.3.24","_npmUser":{"name":"zetahernandez","email":"zetahernandez@gmail.com"},"maintainers":[{"name":"zetahernandez","email":"zetahernandez@gmail.com"}]},"0.0.7":{"name":"pdf-to-text","version":"0.0.7","description":"Extract the text from pdf files","main":"index.js","directories":{"test":"test"},"scripts":{"test":"mocha --reporter spec"},"repository":{"type":"git","url":"git+ssh://git@github.com/zetahernandez/pdf-to-text.git"},"keywords":["pdf","text","extract","convert","parse","info","pdf-to-text","pdftotext","nodejs"],"author":{"name":"Fernando Hernandez"},"license":"ISC","bugs":{"url":"https://github.com/zetahernandez/pdf-to-text/issues"},"homepage":"https://github.com/zetahernandez/pdf-to-text","devDependencies":{"mocha":"~1.21.4","should":"~4.0.4"},"gitHead":"34cc4e48bb5f0f7c5fe96918cb5ec4c25318bd70","_id":"pdf-to-text@0.0.7","_shasum":"d1cd75b6a9f3782a14bcdf9fe6bc02f74cd7ecd3","_from":".","_npmVersion":"3.10.10","_nodeVersion":"6.11.2","_npmUser":{"name":"zetahernandez","email":"zetahernandez@gmail.com"},"dist":{"shasum":"d1cd75b6a9f3782a14bcdf9fe6bc02f74cd7ecd3","tarball":"https://registry.npmjs.org/pdf-to-text/-/pdf-to-text-0.0.7.tgz","fileCount":11,"unpackedSize":39235,"integrity":"sha512-NHWB7u/9q+SZ28UtEgJYljamp61j06oldHdvGik1729pzRFLCO4igbZwm0MOUWoIQUz4nla3n+cf3Jh7uiOZwQ==","signatures":[{"keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA","sig":"MEQCICn4Q1GQ4cYqc6pJShdUK3jLqArd+6/b7vtvy8uVyyGBAiAonx69vjUV0uDSQ6CpihFmUo/pjYSHdQmFRI2RriLWoQ=="}]},"maintainers":[{"name":"zetahernandez","email":"zetahernandez@gmail.com"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages","tmp":"tmp/pdf-to-text_0.0.7_1532651215941_0.5213173903877604"},"_hasShrinkwrap":false}},"readme":"# PDF-TO-TEXT\npdf-to-text is a tool to extract text from pdf. for the moment not support ocr scannig to extract text only works for searchable pdf files. This package doesn't have nodejs dependencies. \n\n[![Build Status](https://travis-ci.org/zetahernandez/pdf-to-text.png)](https://travis-ci.org/zetahernandez/pdf-to-text)\n\n## Installation\n\nTo install the module.\n`npm install pdf-to-text`\n\nYou need install the next tools to use this module\n\n\n- pdftotext\n    - pdftotext is used to extract text out of searchable pdf documents\n- pdfinfo\n    - pdfinfo is used to obtain the info of pdf documents\n\n### OSX\nTo begin on OSX, first make sure you have the homebrew package manager installed.\n\n\n**pdftotext** is included as part on the xpdf utilities library. **xpdf** can be installed via homebrew\n``` bash\nbrew install xpdf\n```\n\n### Ubuntu\n\n**pdftotext** is included in the **poppler-utils** library. To installer poppler-utils execute\n``` bash\napt-get install poppler-utils\n```\n\n\n## Usage\n=======\n\n### PDF Info\n\nObtain info from pdf file\n```js\nvar pdfUtil = require('pdf-to-text');\nvar pdf_path = \"absolute_path/to/pdf_file.pdf\";\n\npdfUtil.info(pdf_path, function(err, info) {\n    if (err) throw(err);\n    console.log(info);\n});\n```\n\nIt's retrieve an object with the data info from the pdf file\n\n``` json\n{ \"title\": \"some title\",\n  \"subject\": \"TeX output 2003.10.17:1908\",\n  \"author\": \"Fernando Hernandez\",\n  \"creator\": \"creator name\",\n  \"producer\": \"Acrobat Distiller 4.0 for Windows\",\n  \"creationdate\": 1066428670000,\n  \"moddate\": 1066428687000,\n  \"tagged\": \"no\",\n  \"form\": \"none\",\n  \"pages\": 8,\n  \"encrypted\": \"no\",\n  \"page_size\": \"612 x 792 pts (letter)\",\n  \"file_size\": \"28695 bytes\",\n  \"optimized\": \"yes\",\n  \"pdf_version\": \"1.2\" \n  }\n```\n\n### PDF Text extract\n\nYou can extract text by a range of pages given an option object with **from** and **to** properties, or simply omit this option to extract all text from the pdf file\n\n```js\nvar pdfUtil = require('pdf-to-text');\nvar pdf_path = \"absolute_path/to/pdf_file.pdf\";\n\n//option to extract text from page 0 to 10\nvar option = {from: 0, to: 10};\n\npdfUtil.pdfToText(upload.path, option, function(err, data) {\n  if (err) throw(err);\n  console.log(data); //print text    \n});\n\n//Omit option to extract all text from the pdf file\npdfUtil.pdfToText(upload.path, function(err, data) {\n  if (err) throw(err);\n  console.log(data); //print all text    \n});\n```\n\n\n## Tests\n\nTo test that your system satisfies the needed dependencies and that module is functioning correctly execute the command in the pdf-to-text module folder\n```\ncd <project_root>/node_modules/pdf-to-text\nnpm test\n```\n","maintainers":[{"name":"zetahernandez","email":"zetahernandez@gmail.com"}],"time":{"modified":"2022-06-23T16:36:45.729Z","created":"2014-10-08T05:52:38.322Z","0.0.0":"2014-10-08T05:52:38.322Z","0.0.1":"2014-10-08T05:58:40.792Z","0.0.2":"2014-10-08T07:36:19.134Z","0.0.3":"2014-10-08T07:37:57.821Z","0.0.4":"2014-10-08T07:45:16.018Z","0.0.5":"2014-10-10T12:38:47.417Z","0.0.6":"2014-10-11T00:27:29.552Z","0.0.7":"2018-07-27T00:26:56.056Z"},"homepage":"https://github.com/zetahernandez/pdf-to-text","keywords":["pdf","text","extract","convert","parse","info","pdf-to-text","pdftotext","nodejs"],"repository":{"type":"git","url":"git+ssh://git@github.com/zetahernandez/pdf-to-text.git"},"author":{"name":"Fernando Hernandez"},"bugs":{"url":"https://github.com/zetahernandez/pdf-to-text/issues"},"license":"ISC","readmeFilename":"README.md","users":{"zetahernandez":true,"stany":true,"ahsanshafiq":true,"nickeltobias":true}}