from urllib.request import urlopen import re """ 爬虫,爬一个豆瓣网,把爬出来的存储到一个文件 """ def get_request(url): """ 把网址变为源码,因为计算机只能读懂源码,然后吧源码变为utf-8的格式 :param url: :return: """ ret = urlopen(url) return ret.read().decode(‘utf-8‘) def get_findall(s): """ 把源码的utf-8的正则显示出来,满足的就以列表打印出来 :param s: :return: """ ret = re.findall( ‘<div class="item">.*?<div class="pic">.*?<em.*?>(?P<id>\d.).*?<span class="title">.*?(?P<name>.*?)</span>‘ ‘.*?<span class="rating_num".*?>(?P<arg>.*?)</span>.*?<span>(?P<cou>.*?)评价</span>‘, s, re.S) return ret def get_ur(w): """ 调用函数。 :param w: :return: """ url = ‘https://movie.douban.com/top250?start=%s&filter=‘ % w ret = get_request(url) ret = get_findall(ret) return ret con = 0 while con < 30: ret = get_ur(con) with open(‘电影‘, ‘w‘, encoding=‘utf-8‘) as f: if ret: try: a = tuple(ret) b = list(a) f.write(str(b)) except Exception: print(‘hehe1‘) f.close() print(ret)
原文地址:https://www.cnblogs.com/python884/p/9982548.html
时间: 2024-10-14 06:12:48