parent
a5c2a4494d
commit
31af973fd4
@ -0,0 +1,45 @@
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
import re
|
||||
|
||||
headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36 Edg/128.0.0.0' }
|
||||
# 获取搜索结果页面的内容
|
||||
def get_search_page(search_url):
|
||||
response = requests.get(search_url, headers=headers)
|
||||
response.raise_for_status() # 确保请求成功
|
||||
return response.text
|
||||
|
||||
# 提取页面中所有视频的链接
|
||||
def extract_video_links(page_content):
|
||||
soup = BeautifulSoup(page_content, 'html.parser')
|
||||
video_links = []
|
||||
for a_tag in soup.select(".video-list.row div.bili-video-card > div > a"):
|
||||
link = a_tag.get('href')
|
||||
video_links.append(link)
|
||||
|
||||
return video_links
|
||||
|
||||
# 提取视频的BV号
|
||||
def extract__BV(video_url):
|
||||
video_id_match = re.search(r'/video/([^/]+)', video_url)
|
||||
if video_id_match:
|
||||
return video_id_match.group(1)
|
||||
return None
|
||||
|
||||
|
||||
# 主函数
|
||||
def main(search_url):
|
||||
page_content = get_search_page(search_url)
|
||||
video_links = extract_video_links(page_content)
|
||||
bvs = []
|
||||
for link in video_links:
|
||||
bv = extract__BV(link)
|
||||
if bv:
|
||||
bvs.append(bv)
|
||||
return(bvs)
|
||||
|
||||
search_url = 'https://search.bilibili.com/all?keyword=2024巴黎奥运会'
|
||||
aa = main(search_url)
|
||||
print(aa)
|
||||
|
||||
|
Loading…
Reference in new issue