19 lines
722 B
Python
19 lines
722 B
Python
import requests
|
|
from bs4 import BeautifulSoup
|
|
import csv
|
|
import json
|
|
import time
|
|
headers = {
|
|
'User-Agent':'mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML,like Gecko) Chrome/120.0.0.0 Safari/537.36'
|
|
}
|
|
movies_data = []
|
|
for page in range(10):
|
|
url = f'https://movie.douban.com/top250?start={page * 25}'
|
|
response = requests.get(url, headers=headers)
|
|
soup = BeautifulSoup(response.text,'html.parser')
|
|
for item in soup.find_all('div',class_='item'):
|
|
title_info = item.find('div',class_='hd').find('a').get_text(strip=Ture).replace('\n','')
|
|
info = item.find('div',class_='bd').p.get_text(strip=True).split('\n')[0]
|
|
movie = {
|
|
|
|
} |