使用Python3.4提取PDF文本

Question

pdf文件中的文本是文本格式，不是扫描的。 PDFMiner不支持python3，有其他解决方案吗？

Answer 1

还有 pdfminer2 分支，支持 python 3.4，可通过 pip3 获得。 https://github.com/metachris/pdfminer

This thread帮我把一些东西拼凑在一起。

from urllib.request import urlopen
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from io import StringIO, BytesIO

def readPDF(pdfFile):
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)

    interpreter = PDFPageInterpreter(rsrcmgr, device)
    password = ""
    maxpages = 0
    caching = True
    pagenos=set()
    for page in PDFPage.get_pages(pdfFile, pagenos, maxpages=maxpages, password=password,caching=caching, check_extractable=True):
        interpreter.process_page(page)

    device.close()
    textstr = retstr.getvalue()
    retstr.close()
    return textstr

if __name__ == "__main__":
    #scrape = open("../warandpeace/chapter1.pdf", 'rb') # for local files
    scrape = urlopen("http://pythonscraping.com/pages/warandpeace/chapter1.pdf") # for external files
    pdfFile = BytesIO(scrape.read())
    outputString = readPDF(pdfFile)
    print(outputString)
    pdfFile.close()