pdf_url_text.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| importrequests | |
| frompdfminer.pdfinterpimportPDFResourceManager, PDFPageInterpreter | |
| frompdfminer.converterimportTextConverter | |
| frompdfminer.layoutimportLAParams | |
| frompdfminer.pdfpageimportPDFPage | |
| fromioimportStringIO, BytesIO | |
| defconvert_pdf_to_txt(url, pages=None): | |
| ifnotpages: | |
| pagenums=set() | |
| else: | |
| pagenums=set(pages) | |
| output=StringIO() | |
| manager=PDFResourceManager() | |
| converter=TextConverter(manager, output, laparams=LAParams()) | |
| interpreter=PDFPageInterpreter(manager, converter) | |
| r=requests.get(url) | |
| infile=BytesIO(r.content) | |
| forpageinPDFPage.get_pages(infile, pagenums): | |
| interpreter.process_page(page) | |
| infile.close() | |
| converter.close() | |
| text=output.getvalue() | |
| output.close() | |
| returntext | |
| if__name__=='__main__': | |
| url=input("Enter URL of PDF from which to extract text: ") | |
| # Example URL: https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf | |
| # Output: | |
| # >>> Dummy PDF file | |
| output=convert_pdf_to_txt(url) | |
| print(output) |
