|
8鱼币
- import requests
- import bs4
- import re
- def open_url(url):
- headers = {
- "User-Agent":"Mozilla/5.0 (Windows NT 6.1; Win64; x64)"
- "AppleWebKit/537.36 (KHTML, like Gecko)"
- "Chrome/90.0.4430.85 Safari/537.36"
- }
- res = requests.get(url,headers=headers)
- return res
- def find_movies(res):
-
- soup = bs4.BeautifulSoup(res.text,'html.parser')
- movise = []
- targets = soup.find_all("div",class_="hd")
- for each in targets:
- movies.append(each.a.span.text)
- ranks = []
- targets = soup.find_all("div",class_="bd")
- for each in targets:
- try:
- messages.append(each.p.text.split('\n')[1].strip()+each.p.text.split('\n')[2].strip())
-
- except:
- continue
- result = []
- length = len(movies)
- for i in range(length):
- result.append(movies[i]+ranks[i]+messages[i]+'\n')
- return result
- def main():
- host = "https://movie.douban.com/top250"
- res = open_url(host)
- depth = find_depth(res)
- result = []
- for i in range(depth):
- url = host+'/?start='+str(25*i)
- res = open_url(url)
- result.extend(find_movies(res))
- with open("豆瓣TOP250电影.txt","w",encoding="utf-8")as f:
- for each in result:
- f.write(each)
- if __name__ == "__main__":
- main()
复制代码
|
-
|