diff --git a/BV.py b/BV.py deleted file mode 100644 index 81ea98f..0000000 --- a/BV.py +++ /dev/null @@ -1,45 +0,0 @@ -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) - - diff --git a/danmu.py b/danmu.py deleted file mode 100644 index a0d9a03..0000000 --- a/danmu.py +++ /dev/null @@ -1,13 +0,0 @@ -import requests -from bs4 import BeautifulSoup -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' } -response = requests.get("https://api.bilibili.com/x/v1/dm/list.so?oid=1512399639", headers=headers) #要爬取的网址 -response.encoding='utf-8' #编码方式 -html = response.text -soup = BeautifulSoup(html) #使用beautifulsoup库快速查找我们想要的信息 -all_txt = soup.findAll("d") #寻找到所有包含d的行 -txt=[all_txts.attrs ["p"]for all_txts in all_txt] #寻找到所有包含d的行中属性为p的值,这里边包含了弹幕的虚拟id等 -txtss=[all_txts.string for all_txts in all_txt] #寻找到所有包含d的行中的字符串数据,即弹幕内容 -txtsss=[txts.replace(' ','') for txts in txtss] #将字符串中的空格消除掉 -print(txtsss) ###打印便可看见一条条弹幕的属性和内容了。 -