bilibili音视频爬虫程序

Bilibili.py

@@ -0,0 +1,47 @@
+import json
+import requests
+import re
+
+url = 'https://www.bilibili.com/video/BV1H7421T7zx/?spm_id_from=333.337.search-card.all.click&vd_source=f6247aa12dae1ff1bce74ef0af381757'
+
+def GetResponse(url):
+    headers = {
+        'accept': 'text / html, application / xhtml + xml, application / xml;q = 0.9, image / avif, image / webp, image / apng, * / *;q = 0.8, application / signed - exchange;v = b3;q = 0.7',
+        'accept - encoding': 'gzip, deflate',
+        'accept - language': 'zh - CN, zh;q = 0.9, en;q = 0.8, en - GB;q = 0.7, en - US;q = 0.6',
+        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.6261.95 Safari/537.36',
+        'Referer':'https://search.bilibili.com/all?vt=44591831&keyword=%E8%B0%81%E7%94%B5%E5%90%89%E4%BB%96%E8%B0%B1&from_source=webtop_search&spm_id_from=333.1007&search_source=2'
+    }
+    response = requests.get(url = url,headers = headers)
+    return response
+
+def GetVideoInfo():
+    response = GetResponse(url = url)
+    html = response.text
+    info = re.findall('<script>window.__playinfo__=(.*?)</script>', html)[0]
+    json_data = json.loads(info)
+
+    audio_url = json_data['data']['dash']['audio'][0]['baseUrl']
+    video_url = json_data['data']['dash']['video'][0]['baseUrl']
+    title = re.findall('<title data-vue-meta="true">(.*?)</title>', html)
+
+    if title:
+        title = title[0]
+    else:
+        return None
+
+    return (title, audio_url, video_url)
+
+def Save(title,audio_url,video_url):
+    audio_content = GetResponse(url = audio_url).content
+    video_content = GetResponse(url = video_url).content
+    with open('bili\\' + title + '.mp3', mode = 'wb') as audio:
+        audio.write(audio_content)
+    with open('bili\\' + title + '.mp4', mode = 'wb') as video:
+        video.write(video_content)
+
+
+
+if __name__ == '__main__':
+    title,audio_url,video_url = GetVideoInfo()
+    Save(title, audio_url, video_url)