30 lines
781 B
Plaintext
30 lines
781 B
Plaintext
import requests
|
||
from bs4 import BeautifulSoup
|
||
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"
|
||
}
|
||
|
||
all_movies = []
|
||
|
||
for page in range(0, 250, 25):
|
||
url = f"https://movie.douban.com/top250?start={page}&filter="
|
||
print(f"正在爬取第 {page//25 + 1} 页：{url}")
|
||
|
||
response = requests.get(url, headers=headers)
|
||
response.encoding = "utf-8"
|
||
soup = BeautifulSoup(response.text, "html.parser")
|
||
|
||
|
||
items = soup.find_all("div", class_="item")
|
||
for item in items:
|
||
title = item.find("span", class_="title").get_text(strip=True)
|
||
all_movies.append(title)
|
||
print(title)
|
||
|
||
|
||
time.sleep(1)
|
||
|
||
|
||
print(f"\n一共爬到电影：{len(all_movies)} 部") |