45 lines
1.4 KiB
Python
45 lines
1.4 KiB
Python
import requests
|
|
from bs4 import BeautifulSoup
|
|
import json
|
|
|
|
# 目标网址与请求头（题目强制要求请求头）
|
|
url = "https://exam.detr.top/exam-b-movies"
|
|
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"
|
|
}
|
|
|
|
# 一次性请求获取全部网页数据
|
|
resp = requests.get(url, headers=headers)
|
|
resp.encoding = resp.apparent_encoding
|
|
html_text = resp.text
|
|
|
|
# 保存原始网页到data/movies.html
|
|
with open("./data/movies.html", "w", encoding="utf-8") as f:
|
|
f.write(html_text)
|
|
|
|
# 解析表格电影数据
|
|
soup = BeautifulSoup(html_text, "html.parser")
|
|
movie_rows = soup.select("table tr")[1:] # 跳过表头
|
|
movies = []
|
|
data_id = "movie_2026"
|
|
|
|
for row in movie_rows:
|
|
tds = row.find_all("td")
|
|
movie_item = {
|
|
"id": tds[0].text.strip(),
|
|
"title": tds[0].text.strip(),
|
|
"director": tds[1].text.strip(),
|
|
"year": int(tds[2].text.strip()),
|
|
"rating": float(tds[3].text.strip()),
|
|
"duration": int(tds[4].text.strip()),
|
|
"genre": tds[5].text.strip(),
|
|
"actors_count": int(tds[6].text.strip())
|
|
}
|
|
movies.append(movie_item)
|
|
|
|
# 保存json文件到data目录
|
|
out = {"data_id": data_id, "movies": movies}
|
|
with open("./data/movies.json", "w", encoding="utf-8") as f:
|
|
json.dump(out, f, ensure_ascii=False, indent=2)
|
|
|
|
print("文件生成完毕") |