python网络数据采集16 pdf

[python]代码库

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() # pdf资源管理对象
    retstr = StringIO() # StringIO 模块用于在内存缓冲区中读写数据
    laparams = LAParams() # 创建一个PDF设备对象
    device = TextConverter(rsrcmgr,retstr,laparams=laparams) # TextConverter文本转换器

    process_pdf(rsrcmgr,device,pdfFile) # (资源管理对象，转换器，url链接)
    device.close()

    content = retstr.getvalue() # getvalue返回对象retstr中的所有数据
    retstr.close()
    return content

pdfFile = urlopen('http://pythonscraping.com/pages/warandpeace/chapter1.pdf')
outputString = readPDF(pdfFile)
print(outputString)
pdfFile.close()