You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
43 lines
1.2 KiB
43 lines
1.2 KiB
5 months ago
|
import requests
|
||
|
|
from bs4 import BeautifulSoup
|
||
|
|
import csv
|
||
|
|
|
||
|
|
url='https://movie.douban.com/subject/1306809/comments?status=P'
|
||
|
|
headers = {
|
||
|
|
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'
|
||
|
|
}
|
||
|
|
response = requests.get(url, headers=headers)
|
||
|
|
source=response.text
|
||
|
|
#print(source)
|
||
|
|
soup = BeautifulSoup(source, 'lxml')
|
||
|
|
comments = soup.find_all('div', class_='comment-item')
|
||
|
|
|
||
|
|
run=[]
|
||
|
|
|
||
|
|
for comment in comments:
|
||
|
|
title=comment.select(".comment-info>a")
|
||
|
|
for t1 in title:
|
||
|
|
print(t1.get_text())
|
||
|
|
t2=t1.get_text(strip=True)
|
||
|
|
run.append([t2])
|
||
|
|
|
||
|
|
time=comment.select(".comment-time")
|
||
|
|
for m1 in time:
|
||
|
|
print(m1.get_text())
|
||
|
|
m2=m1.get_text(strip=True)
|
||
|
|
run.append([m2])
|
||
|
|
|
||
|
|
content = comment.select('p>span')
|
||
|
|
for p1 in content:
|
||
|
|
print(p1.get_text())
|
||
|
|
p2=p1.get_text(strip=True)
|
||
|
|
run.append([p2])
|
||
|
|
|
||
|
|
with open('生化危机.csv',mode='w',encoding='utf-8',newline='') as f:
|
||
|
|
csv_writer = csv.writer(f)
|
||
|
|
for c1 in run:
|
||
|
|
csv_writer.writerow(c1)
|
||
|
|
print("下载完成")
|
||
|
|
|
||
|
|
|