爬虫豆瓣电影top250代码和收获

最新推荐文章于 2024-06-20 11:30:14 发布

原创

最新推荐文章于 2024-06-20 11:30:14 发布 · 2.2k 阅读

4 ·

CC 4.0 BY-SA版权

文章标签：

#爬虫 #正则表达式

# -*- coding:utf-8 -*-
import urllib2
import re
class MovieTop250 :
    def __init__(self):
        self.start = 0
        self.movielist = []

    def getPage(self):
        try:
            headers = {"User-Agent" : "Mozilla/5.0(Windows NT 6.1;WOW64)"}
            url = "https://movie.douban.com/top250?start="+str(self.start)
            request = urllib2.Request(url = url,headers = headers)
            response = urllib2.urlopen(request)
            page = response.read()
            pageNum = str(self.start / 25)
            print "正在抓取第" + pageNum + "页"
            return page

        except urllib2.URLError,e:
            print e.reason
    def getMovie(self):
        pattern = re.compile('<em.*?class="">(.*?)</em>.*?'#网页源代码中属性那里仅有class，但写正则表达式要写成class=""
                             +'<a.*?>.*?<span class="title">(.*?)</span>.*?'
                             +'<span class="\w{5}">(.*?)</span>.*