Skip to content

Instantly share code, notes, and snippets.

Created March 12, 2016 14:48
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save anonymous/e837f2f5d9c6c57d7db8 to your computer and use it in GitHub Desktop.
Save anonymous/e837f2f5d9c6c57d7db8 to your computer and use it in GitHub Desktop.
#coding=utf-8
import json
import requests
import re
class spprec(object):
def __init__(self, url):
self.session = requests.session()
self.session.headers.update({
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.116 Safari/537.36'
})
self.url = url
self.post_data = {}
def getInfo(self, num):
if len(self.post_data) == 0:
res = self.session.get(self.url)
else:
self.post_data['__EVENTARGUMENT'] = num
self.post_data["__EVENTTARGET"] = "MoreInfoList1$Pager"
res = self.session.post(url=self.url, data=self.post_data)
result = re.findall('<input type="hidden" name="([^"]+)" id="([^"]+)" value="([^"]+)" />', res.text, re.S)
post_data = {}
for item in result:
post_data.update({item[0]: item[2]})
self.post_data = post_data
result = re.findall('<a href="(/sczw/InfoDetail/Default.aspx[^"]+)" target="_blank" title="([^"]+)"', res.text, re.S)
return result
obj = spprec("http://www.spprec.com/sczw/jyfwpt/005001/005001001/MoreInfo.aspx?CategoryNum=005001001")
for i in xrange(1, 5):
data = obj.getInfo(i)
for item in data:
print item[1]
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment