爬取豆瓣TOP250的电影
大佬，可以帮我看一下这个代码么，我爬取豆瓣250电影排行榜，为什么ranks和messas列表是空的，爬取不到资料和评分，有什么改进的方法么#完整版代码
import requests
import bs4
import re
def open_url(url):
#使用代理
#proxies = (“http”:"127.0.0.1:1080","https":127.0.0.1:1080)
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36'}
#res = requests.get(url,headers=headers,proxies=proxies)
res = requests.get(url,headers=headers)
return res
def find_movies(res):
soup = bs4.BeautifulSoup(res.text,'html.parser')
#电影名
movies = []
targets = soup.find_all('div',class_='hd')
for each in targets:
movies.append(each.a.span.text)
#评分
ranks=[]
targets = soup.find_all('span',class_='rating_num')
for each in targets:
ranks.append('评分:%s' % each.txt)
#资料
messages = []
targets = soup.find_all('div',class_='bd')
for i in targets:
try:
messages.append(each.p.text.split('\n').strip() + each.p.text.split('\n').strip())
except:
continue
result = []
length = len(movies)
for i in range(length):
result.append(movies + ranks + messages + '\n')
return result
#找出有多少个页面
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)
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() 本帖最后由 suchocolate 于 2021-11-16 12:38 编辑
1）ranks.append('评分:%s' % each.txt)# 应该是each.text
2）资料那块: for i in targets: # 应该时for each in targets:
3) result.append(movies + ranks + messages + '\n')# 应该是 result.append(movies + '\t' +ranks + '\t' + messages + '\t'+ '\n')
suchocolate 发表于 2021-11-15 18:43
1）ranks.append('评分:%s' % each.txt)# 应该是each.text
2）资料那块: for i in targets: # 应该时for ...
大佬牛逼，谢谢大佬
页:
[1]