##爬取豆瓣电影TOP250
import requests from bs4 import BeautifulSoup import codecs
#定义函数将电影名称和url保存到字典中 dic= {} def get_movie(url): response=requests.get(url) mysoup = BeautifulSoup(response.text,‘html.parser’) for new in mysoup.select(’.item’): moview_url = new.select(‘a’)[0][‘href’] moview_name = new.select(’.title’)[0].text dic[moview_name]=moview_url
#将所有的翻页url保存到列表中 all_url = [] for num in range(0,275,25): all_url.append(‘https://movie.douban.com/top250?start=’+ str(num) + ‘&filter=’)
#遍历url进行每页的电影爬取 for url in all_url: get_movie(url)
#保存在文件中 with codecs.open (‘movie_top250.txt’ , ‘w’ ,encoding =‘utf-8’) as f: for name in dic: f.write(name + ’ '+ dic[name] + ‘\n’)
