爬虫案例-爬取某站视频
import requests
import os
from urllib.parse import urlparse
import subprocess
# 视频和音频URL
video_url = "https://upos-sz-mirrorbd.bilivideo.com/upgcxcode/46/89/28747958946/28747958946-1-100022.m4s"
audio_url = "https://cn-gdgz-gd-live-02.bilivideo.com/upgcxcode/46/89/28747958946/28747958946-1-30216.m4s"
# 请求头
header = {
"Referer": "https://www.bilibili.com/video/av576765795?spm_id_from=333.788.player.player_end_recommend_autoplay",
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/134.0.0.0 Safari/537.36 Edg/134.0.0.0"
}
# 视频请求参数
video_params = {
"e": "ig8euxZM2rNcNbdlhoNvNC8BqJIzNbfqXBvEqxTEto8BTrNvN0GvT90W5JZMkX_YN0MvXg8gNEV4NC8xNEV4N03eN0B5tZlqNxTEto8BTrNvNeZVuJ10Kj_g2UB02J0mN0B5tZlqNCNEto8BTrNvNC7MTX502C8f2jmMQJ6mqF2fka1mqx6gqj0eN0B599M=",
"uipk": "5",
"nbs": "1",
"deadline": "1742734058",
"gen": "playurlv2",
"os": "bdbv",
"oi": "1996673551",
"trid": "236892f04e4743a7a3da62f279953324u",
"mid": "0",
"platform": "pc",
"og": "hw",
"upsig": "d8a8f509632b390e62c65ba33d7b8342",
"uparams": "e,uipk,nbs,deadline,gen,os,oi,trid,mid,platform,og",
"bvc": "vod",
"nettype": "0",
"orderid": "0,3",
"buvid": "362FA75D-BD0F-DC0D-E2AE-34526182765756167infoc",
"build": "0",
"f": "u_0_0",
"agrr": "1",
"bw": "18402",
"logo": "80000000"
}
# 音频请求参数
audio_params = {
"e": "ig8euxZM2rNcNbdlhoNvNC8BqJIzNbfqXBvEqxTEto8BTrNvN0GvT90W5JZMkX_YN0MvXg8gNEV4NC8xNEV4N03eN0B5tZlqNxTEto8BTrNvNeZVuJ10Kj_g2UB02J0mN0B5tZlqNCNEto8BTrNvNC7MTX502C8f2jmMQJ6mqF2fka1mqx6gqj0eN0B599M=",
"uipk": "5",
"nbs": "1",
"deadline": "1742734058",
"gen": "playurlv2",
"os": "bcache",
"oi": "1996673551",
"trid": "0000236892f04e4743a7a3da62f279953324u",
"mid": "0",
"platform": "pc",
"og": "hw",
"upsig": "e0007fe3f8ffbf93d9c37a85134bda3c",
"uparams": "e,uipk,nbs,deadline,gen,os,oi,trid,mid,platform,og",
"cdnid": "6697",
"bvc": "vod",
"nettype": "0",
"orderid": "0,3",
"buvid": "362FA75D-BD0F-DC0D-E2AE-34526182765756167infoc",
"build": "0",
"f": "u_0_0",
"agrr": "1",
"bw": "6238",
"logo": "80000000"
}
# 发送请求并下载视频
video_response = requests.get(video_url, headers=header, params=video_params, timeout=10)
video_response.raise_for_status()
# 发送请求并下载音频
audio_response = requests.get(audio_url, headers=header, params=audio_params, timeout=10)
audio_response.raise_for_status()
# 创建输出目录
output_folder = r"C:/Users/zzx/Desktop/video/"
if not os.path.exists(output_folder):
os.makedirs(output_folder)
# 保存视频文件
video_filename = os.path.basename(urlparse(video_url).path)
video_file_path = os.path.join(output_folder, video_filename)
with open(video_file_path, "wb") as f:
for chunk in video_response.iter_content(chunk_size=1024*1024):
if chunk:
f.write(chunk)
print(f"视频文件已下载：{video_file_path}")
# 保存音频文件
audio_filename = os.path.basename(urlparse(audio_url).path)
audio_file_path = os.path.join(output_folder, audio_filename)
with open(audio_file_path, "wb") as f:
for chunk in audio_response.iter_content(chunk_size=1024*1024):
if chunk:
f.write(chunk)
print(f"音频文件已下载：{audio_file_path}")
# 使用 FFmpeg 合并
output_path = os.path.join(output_folder, "merged_video.mp4")
ffmpeg_path = r"C:\Program Files\ffmpeg\bin\ffmpeg.exe" # 确保路径正确
if not os.path.exists(ffmpeg_path):
raise FileNotFoundError(f"FFmpeg 未找到，请检查路径：{ffmpeg_path}")
ffmpeg_cmd = [
ffmpeg_path,
'-i', video_file_path,
'-i', audio_file_path,
'-c:v', 'copy',
'-c:a', 'copy',
'-strict', 'experimental',
output_path
]
try:
subprocess.run(ffmpeg_cmd,check=True)
print(f"合并完成：{output_path}")
except subprocess.CalledProcessError as e:
print(f"合并失败：{e}")