普通爬虫(糗事百科)

糗事百科爬虫示例

原创于 2018-05-31 19:23:49 发布 · 236 阅读

0 ·

CC 4.0 BY-SA版权

Python 专栏收录该内容

30 篇文章

订阅专栏

import urllib.request
import urllib.error
import re
headers = ("User-Agent","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36")
opener = urllib.request.build_opener()
opener.addheaders = [headers]
urllib.request.install_opener(opener)
for i in range(1,2):
 url = "https://www.qiushibaike.com/8hr/page/"+str(i)+"/"
 pagedata = urllib.request.urlopen(url).read().decode("utf-8","ignore")
 pattern = '<div class="content">.*?<span>(.*?)</span>(.*?)</div>'
 datalist = re.compile(pattern,re.S).findall(pagedata)
 for j in range(0,len(datalist)):
  print("第"+str(i)+"页第"+str(j)+"个段子内容是：")
  print(datalist[j])