CZYC_Pachong/bili_spider.py

# @Author  : @Cloudmistery

"""
tips:错误记录
1.headers请求头设置错误导致文件不可读(就是错了)
2.文件名合法化,不合法的文件名直接创建不了
3.音频和视频需要分开爬取及合成
"""

# 请求模块
import requests
# 正则模块
import re
# json模块
import json
# 合并模块
from moviepy.editor import *
# html
import html as h

# TODO:修改url和cookie,爬不到最高画质的主要原因就是没有更新cookie

# 设置
url = 'https://www.bilibili.com/video/BV1J24y1p75G/?buvid=Y84DF68249678902447EA7D8C8D4E12E9DDC&from_spmid=search.search-result.0.0&is_story_h5=false&mid=VRgCQHIxfkYie40eSwgBqQ%3D%3D&plat_id=114&share_from=ugc&share_medium=iphone&share_plat=ios&share_session_id=37ACC364-AFB3-49B2-AE6D-ECDDEE498D3B&share_source=WEIXIN&share_tag=s_i&timestamp=1737513904&unique_k=JBOVMFJ&up_id=690032002&vd_source=f6247aa12dae1ff1bce74ef0af381757'
A_path = 'Audio/'
V_path = 'Video/'

# Synth_path = 'File/美少女/'
Synth_path = 'File/'

headers = {
    'Referer': url,
    'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36 Edg/131.0.0.0",
    'cookie': "buvid3=94F0FDAB-59F7-39B1-F805-CAA3E07060F661671infoc; b_nut=1729338061; _uuid=96637C82-967A-B8CA-D643-7621093B83AF862008infoc; buvid4=6F50A1B3-D6A1-87A5-1EF3-7AA396E5E35C62385-024101911-WqlszYIbsE%2BQ%2FFD68EQkXA%3D%3D; enable_web_push=DISABLE; LIVE_BUVID=AUTO8117293380854336; header_theme_version=CLOSE; rpdid=|(Y|RJYumR|0J'u~kmJJmJ)u; buvid_fp_plain=undefined; hit-dyn-v2=1; is-2022-channel=1; fingerprint=19cfe92f609986680aa1f2f4ffaa5e5d; PVID=1; DedeUserID=35990046; DedeUserID__ckMd5=bf34a8eab39f0c11; buvid_fp=19cfe92f609986680aa1f2f4ffaa5e5d; blackside_state=1; CURRENT_BLACKGAP=1; CURRENT_QUALITY=80; enable_feed_channel=DISABLE; _tea_utm_cache_20001731={%22creative_id%22:209057374}; CURRENT_FNVAL=4048; b_lsid=F36DB5DB_194D3DCC6B3; bmg_af_switch=1; bmg_src_def_domain=i1.hdslb.com; bili_ticket=eyJhbGciOiJIUzI1NiIsImtpZCI6InMwMyIsInR5cCI6IkpXVCJ9.eyJleHAiOjE3Mzg5ODA0NDksImlhdCI6MTczODcyMTE4OSwicGx0IjotMX0.lcIqSpCGaiPjRY0RAbCO8tOzHdF-VFiDMC-TWAiwIcE; bili_ticket_expires=1738980389; SESSDATA=de21e156%2C1754273250%2C4e042%2A21CjBcyUNyR_qeZY9ycuob2AZJmLM-9fFaPpMpNuKQmHWOenW-tp_d3fn8MLTp_YJhwzESVjFKbXVnLVdFS3d1djZyMU1zcE96UnNYWDVqazBrRk9sZUY4aVVETVY2THNpRVhOQVEzVEx2X2ZCTjdwdkpIazIzWThFTFk3SDV5NGpfLWxOWXQxTWVnIIEC; bili_jct=fdb20597a08eb5fe5869f1b5d45b85b6; sid=qk2ukeq5; bp_t_offset_35990046=1030289008506175488; home_feed_column=4; browser_resolution=1274-920"
}

# 主程序
# 发送请求
response = requests.get(url=url, headers=headers,timeout=(3,7))
html = response.text

# 提取,合法化字符并显示 视频标题
title = re.findall('title="(.*?)"', html)[0]
title = h.unescape(title)

if title:
    illegal_chars = fr'<｜|>\/:"*?'
    def remove_illegal_chars(title_ill):
        for char in illegal_chars:
            title_ill = title_ill.replace(char, " ")
        return title_ill
    title = remove_illegal_chars(title)
print("视频标题:",title)

# 提取视频信息，提取音视频链接
# # TODO:设置数值来声明文件品质,0默认最高
info = re.findall('window.__playinfo__=(.*?)</script>', html)[0]
json_data = json.loads(info)
video_url = json_data['data']['dash']['video'][0]['baseUrl']
audio_url = json_data['data']['dash']['audio'][0]['baseUrl']

# 获取音视频内容并保存
video_content = requests.get(url=video_url, headers=headers).content
audio_content = requests.get(url=audio_url, headers=headers).content
def SaveAudio():
    with open(A_path + title + '.mp3', mode='wb') as a:
        a.write(audio_content)
def SaveVideo():
    with open(V_path + title + '.mp4', mode='wb') as v:
        v.write(video_content)

def ClipVideo():
    time_1 = 0
    time_2 = None
    audio_path = fr"{A_path}{title}{'.mp3'}"
    video_path = fr"{V_path}{title}{'.mp4'}"
    audio = AudioFileClip(audio_path)
    audio_clip = audio.subclip(time_1, time_2)
    video = VideoFileClip(video_path)
    video_clip = video.subclip(time_1, time_2)
    audio_clip = audio_clip.set_duration(video_clip.duration)
    video_clip_with_audio = video_clip.set_audio(audio_clip)
    video_clip_with_audio.write_videofile(fr"{Synth_path}{title}{'.mp4'}", codec="libx264", audio_codec="aac")

def main():
    SaveAudio()
    # SaveVideo()
    # ClipVideo()

if __name__ == '__main__':
    main()