凑个小热闹：python采集《狂飙》评论 - ToB企服应用市场:ToB评测及商务社交产业平台

import requests
import parsel
# 我还录制了详细讲解的视频，直接在这个裙 708525271 自取，包括完整代码
headers = {
'Cookie': '数据我都删除了，建议用自己的',
'Host': '',
'User-Agent': '',
}
for page in range(0, 4000):
print(page)
url = f'https://movie.douban.com/subject/35465232/comments?start={page*20}&limit=20&status=P&sort=new_score'
response = requests.get(url=url, headers=headers)
select = parsel.Selector(response.text)
comments = select.css('.comment-item .comment')
for comment in comments:
name = comment.css('.comment-info a::text').get()
try:
score_str = comment.css('.comment-info .rating::attr(class)').get()
score = score_str.replace('0 rating', '').replace('allstar', '')
except:
score = 0
comment_time = comment.css('.comment-info .comment-time::text').get().strip()
vote_count = comment.css('.comment-vote .votes.vote-count::text').get()
comment_content = comment.css('.comment-content span::text').get()
print(name, score, comment_time, vote_count, comment_content)

复制代码