使用Python爬取糗事百科热门文章
#!/usr/bin/python#coding:utf8
"""
爬取糗事百科热门文章
"""
import urllib2
import re
#模拟浏览器访问，否则无法访问
user_agent = r"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36"
#匹配作者，内容和认为段子好笑的人数
regex1 = re.compile(r'<h2>(.*?)</h2>.*?<div class="content">.*?<span>(.*?)</span>.*?<div class="stats">.*?<i class="number">(.*?)</i>', re.S)
n = 1
for i in range(0,35):
url = "https://www.qiushibaike.com/8hr/page/%s/" %(n)
request = urllib2.Request(url, headers={"User-Agent":user_agent})
response = urllib2.urlopen(request)
response = response.read()
paragraph = regex1.findall(response)
for i in paragraph:
author = i
text = re.sub('<br/>', '\n', i)
count = i
print("作者：%s" %(author))
print("好笑：%s" %(count))
print("内容：%s" %(text))
print("\n")
#注释下面三行就一次性显示所有文章
q = raw_input("退出请输入q/Q，继教看请直接回车：")
if q == "q" or q == "Q":
break
if q == "q" or q == "Q":
break
n += 1
页:
[1]