关键字爬google的pdf

import google

import requests

def download_file(url,index):

local_filename=index+"-"+url.split("/")[-1]

r=requests.get(url,stream=True)

with open(local_filename,"wb") as f:

for chunk in r.iter_content(chunk_size=1024):

if chunk:

f.write(chunk)

f.flush

return local_filename

g=google.search('site:*.gov.ph filetype:pdf',tld='com.hk')

index=1

for url in g:

if url.endswith(".pdf"):

file_path=download_file(url,str(index))

print "downloading:"+url+"->"+file_path

index+=1

print "all download finished"