上传文件至 /
This commit is contained in:
44
爬电影.py
44
爬电影.py
@@ -1,23 +1,23 @@
|
||||
|
||||
|
||||
headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
|
||||
}
|
||||
|
||||
url = 'https://movie.douban.com/top250'
|
||||
|
||||
print('开始爬取豆瓣电影Top250...')
|
||||
response = requests.get(url, headers=headers)
|
||||
print(f'状态码: {response.status_code}')
|
||||
print(f'内容长度: {len(response.text)} 字符')
|
||||
|
||||
html = response.text
|
||||
|
||||
title_pattern = r'<span class="title">([^<]+)</span>'
|
||||
titles = re.findall(title_pattern, html)
|
||||
|
||||
chinese_titles = [t for t in titles if not t.startswith('/')]
|
||||
|
||||
print('电影名称(前10部):')
|
||||
for i, title in enumerate(chinese_titles[:10], 1):
|
||||
|
||||
|
||||
headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
|
||||
}
|
||||
|
||||
url = 'https://movie.douban.com/top250'
|
||||
|
||||
print('开始爬取豆瓣电影Top250...')
|
||||
response = requests.get(url, headers=headers)
|
||||
print(f'状态码: {response.status_code}')
|
||||
print(f'内容长度: {len(response.text)} 字符')
|
||||
|
||||
html = response.text
|
||||
|
||||
title_pattern = r'<span class="title">([^<]+)</span>'
|
||||
titles = re.findall(title_pattern, html)
|
||||
|
||||
chinese_titles = [t for t in titles if not t.startswith('/')]
|
||||
|
||||
print('电影名称(前10部):')
|
||||
for i, title in enumerate(chinese_titles[:10], 1):
|
||||
print(f'{i}. {title}')
|
||||
Reference in New Issue
Block a user