emded 标签
pre标签
-
爬虫爬取pdf文档:
- 下载 pdfminer3k
- 安装
python setup.py install
- 代码
from urllib.request import urlopen
from pdfminer.pdfinterp import PDFResourceManager, process_pdf
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from io import StringIO
from io import open
def readPDF(pdfFile):
rsrcmgr = PDFResourceManager()
retstr = StringIO()
laparams = LAParams()
device = TextConverter(rsrcmgr, retstr, laparams=laparams)
process_pdf(rsrcmgr, device, pdfFile)
device.close()
content = retstr.getvalue()
retstr.close()
return content
pdfFile = urlopen('http://www.cncbinternational.com/_document/about-us/investor-relations/regulatory-disclosure/tc/2014-12-31/Balance-Sheet-Recon-and-Extract-of-Transition-Disclosures-Template_31-December-2014.pdf')
outputString = readPDF(pdfFile)
print(outputString)
pdfFile.close()
4.这个模块读出来的pdf不太标准,要研究下源码