爬取豆瓣top250电影
import requests
import re
import bs4
def open_url(url):
kv = {'user-agent' : 'Mozilla/5.0'}
res = requests.get(url, headers = kv)
return res
def find_movies(res):
soup = bs4.BeautifulSoup(res.text, 'html.parser')
movies = []
targets = soup.find_all('div', class_ = 'hd')
for each in targets:
movies.append(each.a.span.text)
ranks = []
targets = soup.find_all('span', class_ = 'rating_num')
for each in targets:
ranks.append(' 评分 %s ' % each.text)
messages = []
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
results = []
length = len(movies)
for i in range(length):
results.append(movies[i] + ranks[i] + messages[i] + '\n')
return results
def find_depth(res):
soup = bs4.BeautifulSoup(res.text, 'html.parser')
depth = soup.find('span', class_ = 'next').previous_sibling.previous_sibling.text
return int(depth)
def main():
host = 'https://movie.douban.com/top250'
res = open_url(host)
depth = find_depth(res)
results = []
for i in range(depth):
url = host + '?start=' + str(25 * i)
res = open_url(url)
results.extend(find_movies(res))
with open('D:\豆瓣电影top250.txt', 'w', encoding = 'utf-8') as f:
for each in results:
f.write(each)
if __name__ == '__main__':
main()