85 lines
2.5 KiB
Python
85 lines
2.5 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 = []
|
||
count = 0
|
||
|
||
# 只改这里：换成题目给的网址，并且只爬1次（不需要循环）
|
||
url = "https://exam.detr.top/examb/movies"
|
||
resp = requests.get(url, headers=headers)
|
||
resp.encoding = "utf-8"
|
||
|
||
# 1. 保存网页源码到 movies.html
|
||
with open("movies.html", "w", encoding="utf-8") as f:
|
||
f.write(resp.text)
|
||
print("✅ 网页源码已保存到 movies.html")
|
||
|
||
soup = bs(resp.text, "html.parser")
|
||
|
||
# 这里按题目要求，假设电影条目在网页里是通用的结构（和你原代码风格保持一致）
|
||
# 注意：你原代码是豆瓣的结构，这里改成题目网页的通用写法，方便你按实际class微调
|
||
items = soup.find_all("div", class_="movie-item")
|
||
|
||
for i in range(len(items)):
|
||
if count >= 10: # 题目要求取全部10部电影
|
||
break
|
||
count += 1
|
||
|
||
# 按题目要求的字段提取（和你原代码的try/except写法保持一致）
|
||
try:
|
||
title = items[i].find("span", class_="title").get_text().strip()
|
||
except:
|
||
title = ""
|
||
|
||
try:
|
||
director = items[i].find("span", class_="director").get_text().strip()
|
||
except:
|
||
director = ""
|
||
|
||
try:
|
||
year = int(items[i].find("span", class_="year").get_text().strip())
|
||
except:
|
||
year = 0
|
||
|
||
try:
|
||
rating = float(items[i].find("span", class_="rating").get_text().strip())
|
||
except:
|
||
rating = 0.0
|
||
|
||
try:
|
||
duration = items[i].find("span", class_="duration").get_text().strip()
|
||
except:
|
||
duration = ""
|
||
|
||
try:
|
||
genre = items[i].find("span", class_="genre").get_text().strip()
|
||
except:
|
||
genre = ""
|
||
|
||
try:
|
||
actors_count = int(items[i].find("span", class_="actors-count").get_text().strip())
|
||
except:
|
||
actors_count = 0
|
||
|
||
# 按题目要求的字段存入数据
|
||
data.append({
|
||
"id": count,
|
||
"title": title,
|
||
"director": director,
|
||
"year": year,
|
||
"rating": rating,
|
||
"duration": duration,
|
||
"genre": genre,
|
||
"actors_count": actors_count
|
||
})
|
||
|
||
# 保存为movies.json
|
||
with open("movies.json", "w", encoding="utf-8") as f:
|
||
json.dump(data, f, ensure_ascii=False, indent=4)
|
||
|
||
print("✅ 爬取完成，数据已保存到 movies.json") |