|
@@ -7,31 +7,29 @@ tips:错误记录
|
|
3.音频和视频需要分开爬取及合成
|
|
3.音频和视频需要分开爬取及合成
|
|
"""
|
|
"""
|
|
|
|
|
|
-# 请求模块
|
|
|
|
import requests
|
|
import requests
|
|
-# 正则模块
|
|
|
|
import re
|
|
import re
|
|
-# json模块
|
|
|
|
import json
|
|
import json
|
|
-# 合并模块
|
|
|
|
from moviepy.editor import *
|
|
from moviepy.editor import *
|
|
-# html
|
|
|
|
import html as h
|
|
import html as h
|
|
|
|
+import os
|
|
|
|
|
|
-# 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
|
|
|
|
|
|
+# TODO:及时更新url和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×tamp=1737513904&unique_k=JBOVMFJ&up_id=690032002&vd_source=f6247aa12dae1ff1bce74ef0af381757'
|
|
|
|
|
|
+# 设置 请求url 手动创建文件夹
|
|
|
|
+url = 'https://www.bilibili.com/video/BV1SzmKY4ENo/?spm_id_from=333.1387.upload.video_card.click&vd_source=f6247aa12dae1ff1bce74ef0af381757'
|
|
A_path = 'Audio/'
|
|
A_path = 'Audio/'
|
|
V_path = 'Video/'
|
|
V_path = 'Video/'
|
|
|
|
|
|
# Synth_path = 'File/美少女/'
|
|
# Synth_path = 'File/美少女/'
|
|
-Synth_path = 'File/'
|
|
|
|
|
|
+# Synth_path = 'File/电吉他/'
|
|
|
|
+Synth_path = 'Files/'
|
|
|
|
|
|
|
|
+# 需要完整url
|
|
headers = {
|
|
headers = {
|
|
'Referer': url,
|
|
'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"
|
|
|
|
|
|
+ 'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/133.0.0.0 Safari/537.36 Edg/133.0.0.0",
|
|
|
|
+ '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; PVID=1; DedeUserID=35990046; DedeUserID__ckMd5=bf34a8eab39f0c11; blackside_state=1; CURRENT_BLACKGAP=1; enable_feed_channel=ENABLE; _tea_utm_cache_20001731={%22creative_id%22:271609082}; fingerprint=d36c01c87471ab70718bc472c27c52a6; buvid_fp=d36c01c87471ab70718bc472c27c52a6; bili_ticket=eyJhbGciOiJIUzI1NiIsImtpZCI6InMwMyIsInR5cCI6IkpXVCJ9.eyJleHAiOjE3NDU3MzE0OTUsImlhdCI6MTc0NTQ3MjIzNSwicGx0IjotMX0.mKHJFSP71sE3SetILNeShNBopd-nFD8IBLn7DRY40GY; bili_ticket_expires=1745731435; SESSDATA=af67ee36%2C1761024297%2C05147%2A41CjCFXD8lfOe6Y2Wytxly3_3CZxgGO8Wxuw2wiuxq6b-u0e6YmP-Bj-vplF3JFdZSKI8SVlBtQmNFQ3BNRmJCSzR4R0labVhZVzdTMEpucGtPSklVdlROWkpTWHp1OHBKRlQ5M2cyQ1gzMzdmZ2EwSUZxRFFKRUF2RUFZWXZBanY5Q0FSQS10M0lBIIEC; bili_jct=9ebb01c20099662180c2ec6a8ce2d34f; CURRENT_QUALITY=116; b_lsid=211010F35B_1966BEE3984; bmg_af_switch=1; bmg_src_def_domain=i1.hdslb.com; sid=892zno53; home_feed_column=4; browser_resolution=1281-754; bp_t_offset_35990046=1059705780682358784; CURRENT_FNVAL=4048"
|
|
}
|
|
}
|
|
|
|
|
|
# 主程序
|
|
# 主程序
|
|
@@ -42,7 +40,9 @@ html = response.text
|
|
# 提取,合法化字符并显示 视频标题
|
|
# 提取,合法化字符并显示 视频标题
|
|
title = re.findall('title="(.*?)"', html)[0]
|
|
title = re.findall('title="(.*?)"', html)[0]
|
|
title = h.unescape(title)
|
|
title = h.unescape(title)
|
|
|
|
+title = title + "自拟"
|
|
|
|
|
|
|
|
+# 合法化标题
|
|
if title:
|
|
if title:
|
|
illegal_chars = fr'<||>\/:"*?'
|
|
illegal_chars = fr'<||>\/:"*?'
|
|
def remove_illegal_chars(title_ill):
|
|
def remove_illegal_chars(title_ill):
|
|
@@ -53,7 +53,7 @@ if title:
|
|
print("视频标题:",title)
|
|
print("视频标题:",title)
|
|
|
|
|
|
# 提取视频信息,提取音视频链接
|
|
# 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
|
|
|
|
|
|
+# 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]
|
|
info = re.findall('window.__playinfo__=(.*?)</script>', html)[0]
|
|
json_data = json.loads(info)
|
|
json_data = json.loads(info)
|
|
video_url = json_data['data']['dash']['video'][0]['baseUrl']
|
|
video_url = json_data['data']['dash']['video'][0]['baseUrl']
|
|
@@ -62,9 +62,11 @@ audio_url = json_data['data']['dash']['audio'][0]['baseUrl']
|
|
# 获取音视频内容并保存
|
|
# 获取音视频内容并保存
|
|
video_content = requests.get(url=video_url, headers=headers).content
|
|
video_content = requests.get(url=video_url, headers=headers).content
|
|
audio_content = requests.get(url=audio_url, headers=headers).content
|
|
audio_content = requests.get(url=audio_url, headers=headers).content
|
|
|
|
+
|
|
def SaveAudio():
|
|
def SaveAudio():
|
|
with open(A_path + title + '.mp3', mode='wb') as a:
|
|
with open(A_path + title + '.mp3', mode='wb') as a:
|
|
a.write(audio_content)
|
|
a.write(audio_content)
|
|
|
|
+
|
|
def SaveVideo():
|
|
def SaveVideo():
|
|
with open(V_path + title + '.mp4', mode='wb') as v:
|
|
with open(V_path + title + '.mp4', mode='wb') as v:
|
|
v.write(video_content)
|
|
v.write(video_content)
|
|
@@ -82,10 +84,18 @@ def ClipVideo():
|
|
video_clip_with_audio = video_clip.set_audio(audio_clip)
|
|
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")
|
|
video_clip_with_audio.write_videofile(fr"{Synth_path}{title}{'.mp4'}", codec="libx264", audio_codec="aac")
|
|
|
|
|
|
|
|
+ try:
|
|
|
|
+ os.path.exists(video_path)
|
|
|
|
+ os.remove(video_path)
|
|
|
|
+ print(f'文件 {video_path} 已被删除')
|
|
|
|
+ except:
|
|
|
|
+ print(f'无 {video_path} 此文件')
|
|
|
|
+
|
|
|
|
+
|
|
def main():
|
|
def main():
|
|
SaveAudio()
|
|
SaveAudio()
|
|
- # SaveVideo()
|
|
|
|
- # ClipVideo()
|
|
|
|
|
|
+ SaveVideo()
|
|
|
|
+ ClipVideo()
|
|
|
|
|
|
if __name__ == '__main__':
|
|
if __name__ == '__main__':
|
|
main()
|
|
main()
|