V2EX post filter

gistfile1.txt

#!/usr/bin/python
#coding:UTF-8

import urllib2, re
from bs4 import BeautifulSoup

site_url = 'https://www.v2ex.com'
headers = { 'User-Agent' : 'Mozilla/5.0' }

for page_number in range(1, 10):
    
    link = 'https://www.v2ex.com/go/cv?p=%s' % page_number
    req = urllib2.Request(link, None, headers)
    
    page = urllib2.urlopen(req).read()
    soup = BeautifulSoup(page, 'html.parser')
    soup.prettify()

    list = soup.find_all("div", {"id": "TopicsNode"})

    for tag in list:
        tdTags = tag.find_all("span", {"class": "item_title"})
        for tag in tdTags:
            if re.search(u'上海|android', tag.text, re.IGNORECASE):
                print "%s - %s%s" % (tag.text, site_url , tag.find('a')['href'])