爬取思路：

url從網頁上把代碼搞下來
bytes decode ---> utf-8 網頁內容就是我的待匹配的字符串
ret = re.findall(正則，待匹配的字符串), ret 是所有匹配到的內容組成的列表

import re import json from urllib.request import urlopen# (1)re.compile——爬取到文件中def getPage(url):response = urlopen(url)return response.read().decode('utf-8')def parsePage(s):com = re.compile('<div class="item">.*?<div class="pic">.*?<em .*?>(?P<id>\d+).*?<span class="title">(?P<title>.*?)</span>''.*?<span class="rating_num" .*?>(?P<rating_num>.*?)</span>.*?<span>(?P<comment_num>.*?)評價</span>',re.S)ret = com.finditer(s)for i in ret:yield {"id":i.group("id"),"title":i.group("title"),"rating_num":i.group("rating_num"),"comment_num":i.group("comment_num"),}def main(num):url = 'https://movie.douban.com/top250?start=%s&filter=' % numresponse_html = getPage(url)ret = parsePage(response_html)print(ret)f = open("movie_info","a",encoding="utf-8")for obj in ret:print(obj)data = str(obj)f.write(data + "\n")f.close()count = 0 for i in range(10): # 10頁 main(count)count += 25 import re import json from urllib.request import urlopen
# (2)re.findall——打印輸出import re import json from urllib.request import urlopendef getPage(url):response = urlopen(url)return response.read().decode('utf-8')def parsePage(s):ret = re.findall( '<div class="item">.*?<div class="pic">.*?<em .*?>(?P<id>\d+).*?<span class="title">(?P<title>.*?)</span>''.*?<span class="rating_num" .*?>(?P<rating_num>.*?)</span>.*?<span>(?P<comment_num>.*?)評價</span>',s,re.S)return retdef main(num):url = 'https://movie.douban.com/top250?start=%s&filter=' % numresponse_html = getPage(url)ret = parsePage(response_html)print(ret)count = 0 for i in range(10): #10頁 main(count)count += 25

?正則表達式詳解：

?

?

?

轉載于:https://www.cnblogs.com/xc-718/p/9751113.html

總結

以上是生活随笔為你收集整理的简单的爬虫例子——爬取豆瓣Top250的电影的排名、名字、评分、评论数的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。