{"library":"pdfminer2","title":"pdfminer2","description":"A fork of PDFMiner for Python 3. Provides tools for extracting text, images, and metadata from PDF files. Version 20151206 is the last release; the project is largely superseded by pdfminer.six.","language":"python","status":"deprecated","last_verified":"Fri May 01","install":{"commands":["pip install pdfminer2"],"cli":null},"imports":["from pdfminer.pdfparser import PDFParser","from pdfminer.pdfinterp import PDFPageInterpreter"],"auth":{"required":false,"env_vars":[]},"quickstart":{"code":"from pdfminer.pdfparser import PDFParser\nfrom pdfminer.pdfdocument import PDFDocument\nfrom pdfminer.pdfpage import PDFPage\nfrom pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter\nfrom pdfminer.converter import TextConverter\nfrom pdfminer.layout import LAParams\nfrom io import StringIO\n\n# Open PDF file\nwith open('sample.pdf', 'rb') as fh:\n    parser = PDFParser(fh)\n    doc = PDFDocument(parser)\n    rsrcmgr = PDFResourceManager()\n    retstr = StringIO()\n    laparams = LAParams()\n    device = TextConverter(rsrcmgr, retstr, laparams=laparams)\n    interpreter = PDFPageInterpreter(rsrcmgr, device)\n    for page in PDFPage.create_pages(doc):\n        interpreter.process_page(page)\n    text = retstr.getvalue()\n    device.close()\n    retstr.close()\n    print(text)","lang":"python","description":"Extract text from a PDF file using pdfminer2.","tag":null,"tag_description":null,"last_tested":null,"results":[]},"compatibility":null}