44 lines
1.9 KiB
Python
44 lines
1.9 KiB
Python
import requests
|
||
import json
|
||
from bs4 import BeautifulSoup
|
||
|
||
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",
|
||
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
|
||
"Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
|
||
"Referer": "https://exam.detr.top/"
|
||
}
|
||
|
||
url = "https://exam.detr.top/exam-b/movies"
|
||
response = requests.get(url, headers=headers)
|
||
response.encoding = "utf-8"
|
||
|
||
with open("movies.html", "w", encoding="utf-8") as f:
|
||
f.write(response.text)
|
||
|
||
soup = BeautifulSoup(response.text, "html.parser")
|
||
data_id = soup.find("div", {"class": "data-id"}).text.strip() if soup.find("div", {"class": "data-id"}) else "unknown"
|
||
|
||
movies = []
|
||
movie_items = soup.find_all("div", {"class": "movie-item"})
|
||
for item in movie_items[:10]:
|
||
movie = {
|
||
"id": item.find("span", {"class": "movie-id"}).text.strip(),
|
||
"title": item.find("h3", {"class": "movie-title"}).text.strip(),
|
||
"director": item.find("p", {"class": "movie-director"}).text.strip().replace("导演：", ""),
|
||
"year": int(item.find("p", {"class": "movie-year"}).text.strip().replace("上映年份：", "")),
|
||
"rating": float(item.find("span", {"class": "movie-rating"}).text.strip()),
|
||
"duration": int(item.find("p", {"class": "movie-duration"}).text.strip().replace("时长：", "").replace("分钟", "")),
|
||
"genre": item.find("p", {"class": "movie-genre"}).text.strip().replace("类型：", ""),
|
||
"actors_count": int(item.find("p", {"class": "movie-actors"}).text.strip().replace("演员数量：", ""))
|
||
}
|
||
movies.append(movie)
|
||
|
||
final_data = {
|
||
"data_id": data_id,
|
||
"movies": movies
|
||
}
|
||
with open("movies.json", "w", encoding="utf-8") as f:
|
||
json.dump(final_data, f, ensure_ascii=False, indent=4)
|
||
|
||
print("爬取完成，已生成movies.json和movies.html") |