豌豆荚 TOP 排行

wdj_top.py

# encoding=utf8

import urllib2
from bs4 import BeautifulSoup

url = 'http://www.wandoujia.com/top'

opener = urllib2.build_opener()

content = opener.open(url).read()

dom = BeautifulSoup(content)

app_lists = dom.find_all("div", class_='app-rank')

for ndx, list in enumerate(app_lists):
    print('----------')
    print list.find('h2').string
    print('----------')

    apps = list.find_all('span', class_='txt')

    for app in apps:
        print app.string

    print ('')