135 lines
4.5 KiB
Python
135 lines
4.5 KiB
Python
import requests
|
||
from bs4 import BeautifulSoup
|
||
import json
|
||
import csv
|
||
import os
|
||
|
||
headers = {
|
||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0;Win64; x64) AppleWebKit/537.36(KHTML,like Gecko) Chrome/91.8.4472.124 Safari/537.36'
|
||
}
|
||
|
||
movies = []
|
||
|
||
for start in range(0, 250, 25):
|
||
url = f'https://movie.douban.com/top250?start={start}'
|
||
response = requests.get(url, headers=headers)
|
||
soup = BeautifulSoup(response.text, 'html.parser')
|
||
|
||
for item in soup.find_all('div', class_='item'):
|
||
rank_tag = item.find('em')
|
||
rank = rank_tag.text if rank_tag else '未知排名'
|
||
|
||
title_tag = item.find('span', class_='title')
|
||
if title_tag:
|
||
title = title_tag.text
|
||
else:
|
||
title = "未找到标题"
|
||
print(f"在这个item里没找到标题:{item}")
|
||
|
||
other_tag = item.find('span', class_='other')
|
||
other_title = other_tag.text.strip() if other_tag else ""
|
||
|
||
if other_title.startswith('/'):
|
||
other_title = other_title[1:].strip()
|
||
|
||
rating_tag = item.find('span', class_='rating_num')
|
||
rating = rating_tag.text if rating_tag else "未知评分"
|
||
|
||
inq_tag = item.find('span', class_='inq')
|
||
inq = inq_tag.text.strip() if inq_tag else ""
|
||
|
||
playable_tag = item.find('span', class_='playable')
|
||
if playable_tag:
|
||
year_tag = playable_tag.find_previous_sibling('span', class_='year')
|
||
year = year_tag.text.strip('()') if year_tag else "未知年份"
|
||
else:
|
||
year_tag = item.find('span', class_='year')
|
||
year = year_tag.text.strip('()') if year_tag else "未知年份"
|
||
|
||
img_tag = item.find('img')
|
||
poster_url = img_tag['src'] if img_tag else ""
|
||
|
||
movies.append({
|
||
"rank": int(rank),
|
||
"title": title,
|
||
"en_title": other_title,
|
||
"rating": rating,
|
||
"quote": inq,
|
||
"year": year,
|
||
"poster_url": poster_url
|
||
})
|
||
if len(movies) >= 10:
|
||
break
|
||
if len(movies) >= 10:
|
||
break
|
||
|
||
with open("movies.txt", "w", encoding="utf-8") as f:
|
||
for movie in movies:
|
||
f.write(movie["title"] + "\n")
|
||
print(" 已保存：movies.txt")
|
||
|
||
with open("movies.csv", "w", encoding="utf-8-sig", newline="") as f:
|
||
writer = csv.writer(f)
|
||
writer.writerow(["排名", "中文名", "英文名", "评分", "简介", "年份"])
|
||
for movie in movies:
|
||
writer.writerow([
|
||
movie["rank"],
|
||
movie["title"],
|
||
movie["en_title"],
|
||
movie["rating"],
|
||
movie["quote"],
|
||
movie["year"]
|
||
])
|
||
print(" 已保存：movies.csv")
|
||
|
||
with open("movies.json", "w", encoding="utf-8") as f:
|
||
json.dump(movies, f, ensure_ascii=False, indent=4)
|
||
print(" 已保存：movies.json")
|
||
|
||
high_rating_movies = []
|
||
with open("movies.csv", "r", encoding="utf-8-sig") as f:
|
||
reader = csv.DictReader(f)
|
||
for row in reader:
|
||
if float(row["评分"]) > 9.5:
|
||
high_rating_movies.append(row)
|
||
|
||
print("\n=== 评分高于9.5的电影 ===")
|
||
for m in high_rating_movies:
|
||
print(f"{m['排名']} {m['中文名']} {m['评分']}")
|
||
|
||
with open("high_rating.csv", "w", encoding="utf-8-sig", newline="") as f:
|
||
writer = csv.DictWriter(f, fieldnames=high_rating_movies[0].keys())
|
||
writer.writeheader()
|
||
writer.writerows(high_rating_movies)
|
||
print(" 已保存：high_rating.csv")
|
||
|
||
with open("movies.json", "r", encoding="utf-8") as f:
|
||
movie_data = json.load(f)
|
||
|
||
ratings = [float(m["rating"]) for m in movie_data]
|
||
avg_rating = sum(ratings) / len(ratings)
|
||
max_rating = max(ratings)
|
||
top_movies = [m for m in movie_data if float(m["rating"]) == max_rating]
|
||
|
||
print(f"\n=== 统计信息 ===")
|
||
print(f"前10部电影平均分：{avg_rating:.2f}")
|
||
print(f"最高评分：{max_rating}")
|
||
for m in top_movies:
|
||
print(f"评分最高的电影：{m['title']}")
|
||
|
||
poster_folder = "movie_posters"
|
||
os.makedirs(poster_folder, exist_ok=True)
|
||
|
||
for movie in movies:
|
||
try:
|
||
if movie["poster_url"]:
|
||
img_resp = requests.get(movie["poster_url"], headers=headers)
|
||
|
||
filename = f"{poster_folder}/{movie['rank']}_{movie['title']}.jpg"
|
||
with open(filename, "wb") as f:
|
||
f.write(img_resp.content)
|
||
print(f" 已下载海报：{movie['title']}")
|
||
except Exception as e:
|
||
print(f" 海报下载失败：{movie['title']}，错误：{e}")
|
||
|
||
print("\n 所有任务全部完成！") |