上传文件至 /
This commit is contained in:
47
26.03.31 43test4.py
Normal file
47
26.03.31 43test4.py
Normal file
@@ -0,0 +1,47 @@
|
||||
import requests
|
||||
import os
|
||||
import json
|
||||
|
||||
# 模拟：从网页提取的海报URL（实际应从HTML中提取）
|
||||
poster_urls = [
|
||||
{'rank': 1, 'title': '肖申克的救赎', 'url': 'https://img3.doubanio.com/view/photo/s_ratio_poster/public/p480747492.jpg'},
|
||||
{'rank': 2, 'title': '霸王别姬', 'url': 'https://img1.doubanio.com/view/photo/s_ratio_poster/public/p2911205318.jpg'},
|
||||
{'rank': 3, 'title': '泰坦尼克号', 'url': 'https://img9.doubanio.com/view/photo/s_ratio_poster/public/p457760035.jpg'},
|
||||
]
|
||||
|
||||
headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
|
||||
}
|
||||
|
||||
# 创建目录
|
||||
os.makedirs('posters', exist_ok=True)
|
||||
|
||||
# 保存图片
|
||||
saved_info = []
|
||||
for info in poster_urls:
|
||||
try:
|
||||
# 发送请求获取图片
|
||||
response = requests.get(info['url'], headers=headers, timeout=10)
|
||||
image_data = response.content
|
||||
|
||||
# 保存图片
|
||||
filename = f"posters/{info['rank']}_{info['title']}.jpg"
|
||||
with open(filename, 'wb') as f:
|
||||
f.write(image_data)
|
||||
|
||||
saved_info.append({
|
||||
'rank': info['rank'],
|
||||
'title': info['title'],
|
||||
'filename': filename,
|
||||
'size': len(image_data)
|
||||
})
|
||||
print(f'已保存: {filename} ({len(image_data)} bytes)')
|
||||
|
||||
except Exception as e:
|
||||
print(f'下载失败 {info["title"]}: {e}')
|
||||
|
||||
# 保存图片信息到JSON
|
||||
with open('posters/info.json', 'w', encoding='utf-8') as f:
|
||||
json.dump(saved_info, f, ensure_ascii=False, indent=2)
|
||||
|
||||
print('\n图片信息已保存到 posters/info.json')
|
||||
85
26.03.31 43test5.py
Normal file
85
26.03.31 43test5.py
Normal file
@@ -0,0 +1,85 @@
|
||||
import requests
|
||||
import re
|
||||
import csv
|
||||
import json
|
||||
import os
|
||||
import time
|
||||
|
||||
def crawl_douban_top10():
|
||||
"""爬取豆瓣Top10电影信息"""
|
||||
|
||||
print('开始爬取豆瓣电影Top10...')
|
||||
|
||||
# 1. 爬取页面
|
||||
headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36',
|
||||
'Accept': 'text/html,application/xhtml+xml',
|
||||
}
|
||||
url = 'https://movie.douban.com/top250'
|
||||
|
||||
response = requests.get(url, headers=headers, timeout=10)
|
||||
html = response.text
|
||||
|
||||
# 2. 提取数据
|
||||
# 电影名称（中文）
|
||||
title_cn = re.findall(r'<span class="title">([^<&]+)</span>', html)
|
||||
# 评分
|
||||
ratings = re.findall(r'<span class="rating_num"[^>]*>(\d+\.?\d*)</span>', html)
|
||||
# 经典台词
|
||||
quotes = re.findall(r'<span class="inq">([^<]+)</span>', html)
|
||||
|
||||
# 3. 整理数据
|
||||
movies = []
|
||||
cn_index = 0
|
||||
for i in range(10):
|
||||
# 跳过英文名
|
||||
while cn_index < len(title_cn) and title_cn[cn_index].startswith('/'):
|
||||
cn_index += 1
|
||||
|
||||
movie = {
|
||||
'rank': i + 1,
|
||||
'title': title_cn[cn_index] if cn_index < len(title_cn) else '',
|
||||
'rating': ratings[i] if i < len(ratings) else '',
|
||||
'quote': quotes[i] if i < len(quotes) else ''
|
||||
}
|
||||
movies.append(movie)
|
||||
cn_index += 1
|
||||
|
||||
return movies
|
||||
|
||||
def save_to_csv(movies, filename):
|
||||
"""保存为CSV"""
|
||||
with open(filename, 'w', encoding='utf-8', newline='') as f:
|
||||
writer = csv.DictWriter(f, fieldnames=['rank', 'title', 'rating', 'quote'])
|
||||
writer.writeheader()
|
||||
writer.writerows(movies)
|
||||
print(f'CSV已保存: {filename}')
|
||||
|
||||
def save_to_json(movies, filename):
|
||||
"""保存为JSON"""
|
||||
with open(filename, 'w', encoding='utf-8') as f:
|
||||
json.dump(movies, f, ensure_ascii=False, indent=2)
|
||||
print(f'JSON已保存: {filename}')
|
||||
|
||||
def main():
|
||||
# 创建输出目录
|
||||
os.makedirs('douban_output', exist_ok=True)
|
||||
|
||||
# 爬取数据
|
||||
movies = crawl_douban_top10()
|
||||
|
||||
# 保存文件
|
||||
save_to_csv(movies, 'douban_output/movies.csv')
|
||||
save_to_json(movies, 'douban_output/movies.json')
|
||||
|
||||
# 显示结果
|
||||
print('\n爬取结果：')
|
||||
print('-' * 50)
|
||||
for m in movies:
|
||||
quote_text = f'「{m["quote"]}」' if m['quote'] else ''
|
||||
print(f"{m['rank']}. {m['title']} - 评分: {m['rating']} {quote_text}")
|
||||
|
||||
print('\n完成！')
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
11
movies.csv
Normal file
11
movies.csv
Normal file
@@ -0,0 +1,11 @@
|
||||
rank,title,en_title,rating
|
||||
1,肖申克的救赎,,9.7
|
||||
2,霸王别姬,,9.6
|
||||
3,泰坦尼克号,,9.5
|
||||
4,阿甘正传,,9.5
|
||||
5,千与千寻,,9.4
|
||||
6,美丽人生,,9.5
|
||||
7,星际穿越,,9.4
|
||||
8,这个杀手不太冷,,9.4
|
||||
9,盗梦空间,,9.4
|
||||
10,楚门的世界,,9.4
|
||||
|
72
movies.json
Normal file
72
movies.json
Normal file
@@ -0,0 +1,72 @@
|
||||
[
|
||||
{
|
||||
"rank": 1,
|
||||
"title": "肖申克的救赎",
|
||||
"en_title": "",
|
||||
"rating": "9.7",
|
||||
"quote": ""
|
||||
},
|
||||
{
|
||||
"rank": 2,
|
||||
"title": "霸王别姬",
|
||||
"en_title": "",
|
||||
"rating": "9.6",
|
||||
"quote": ""
|
||||
},
|
||||
{
|
||||
"rank": 3,
|
||||
"title": "泰坦尼克号",
|
||||
"en_title": "",
|
||||
"rating": "9.5",
|
||||
"quote": ""
|
||||
},
|
||||
{
|
||||
"rank": 4,
|
||||
"title": "阿甘正传",
|
||||
"en_title": "",
|
||||
"rating": "9.5",
|
||||
"quote": ""
|
||||
},
|
||||
{
|
||||
"rank": 5,
|
||||
"title": "千与千寻",
|
||||
"en_title": "",
|
||||
"rating": "9.4",
|
||||
"quote": ""
|
||||
},
|
||||
{
|
||||
"rank": 6,
|
||||
"title": "美丽人生",
|
||||
"en_title": "",
|
||||
"rating": "9.5",
|
||||
"quote": ""
|
||||
},
|
||||
{
|
||||
"rank": 7,
|
||||
"title": "星际穿越",
|
||||
"en_title": "",
|
||||
"rating": "9.4",
|
||||
"quote": ""
|
||||
},
|
||||
{
|
||||
"rank": 8,
|
||||
"title": "这个杀手不太冷",
|
||||
"en_title": "",
|
||||
"rating": "9.4",
|
||||
"quote": ""
|
||||
},
|
||||
{
|
||||
"rank": 9,
|
||||
"title": "盗梦空间",
|
||||
"en_title": "",
|
||||
"rating": "9.4",
|
||||
"quote": ""
|
||||
},
|
||||
{
|
||||
"rank": 10,
|
||||
"title": "楚门的世界",
|
||||
"en_title": "",
|
||||
"rating": "9.4",
|
||||
"quote": ""
|
||||
}
|
||||
]
|
||||
Reference in New Issue
Block a user