46 lines
1.3 KiB
Python
46 lines
1.3 KiB
Python
import requests
|
|
from bs4 import BeautifulSoup as bs
|
|
import json
|
|
|
|
headers = {
|
|
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36"
|
|
}
|
|
|
|
|
|
data = []
|
|
for start in range(0, 250, 25):
|
|
url = f"https://movie.douban.com/top250?start={start}&filter="
|
|
resp = requests.get(url, headers=headers)
|
|
resp.encoding = "utf-8"
|
|
soup = bs(resp.text, "html.parser")
|
|
items = soup.find_all("div", class_="item")
|
|
|
|
for item in items:
|
|
|
|
title = item.find("span", class_="title").get_text()
|
|
|
|
|
|
info_text = item.find("div", class_="bd").get_text().strip()
|
|
|
|
info_lines = [line.strip() for line in info_text.split("\n") if line.strip()]
|
|
actors = ""
|
|
for line in info_lines:
|
|
if "主演:" in line:
|
|
actors = line.split("主演:")[-1].strip()
|
|
break
|
|
|
|
|
|
quote = ""
|
|
quote_tag = item.find("p", class_="quote")
|
|
if quote_tag:
|
|
quote = quote_tag.get_text().strip()
|
|
|
|
data.append({
|
|
"title": title,
|
|
"actors": actors,
|
|
"quote": quote
|
|
})
|
|
|
|
print(data)
|
|
with open("movies.json", "w", encoding="utf-8") as f:
|
|
json.dump(data, f, ensure_ascii=False, indent=4) |