def download_subtitle(video_id):
"""
下载video的中英字幕并保存到video model中
:param video_id:
:return:
"""
video = Video.objects.get(video_id=video_id)
options = {
'outtmpl': YOUTUBE_DOWNLOAD_DIR + '\%(title)s-%(id)s.%(ext)s',
# name the file the ID of the video
'verbose': True, # Print various debugging information
'restrictfilenames': True,
'subtitleslangs': ['en', 'zh-Hans'], # 要写成list的形式
# 'convertsubtitles': 'srt',
'subtitlesformat': 'vtt',
'writeautomaticsub': True, # 下载字幕，这里的字幕是youtube自动生成的CC字幕
'skip_download': True,
}
with youtube_dl.YoutubeDL(options) as ydl:
ydl.download([video.youtube_url])
# 只适用于subtitlesformat设置为srt或ass的情况，设置为best则失效
# 字幕名称格式 LG K10 and K7 hands-on-_9coAtC2PZI.en.srt
subtitle_en_filepath = search_keyword_in_file(dir=YOUTUBE_DOWNLOAD_DIR,
keyword=video.video_id
+ ".en",
extend=options.get(
'subtitlesformat',
None))
result = []
if (subtitle_en_filepath.__len__()) == 1:
# 从list中把唯一的一个数据pop出来
video.subtitle_en = subtitle_en_filepath.pop()
result.append(video.subtitle_en)
subtitle_cn_filepath = search_keyword_in_file(dir=YOUTUBE_DOWNLOAD_DIR,
keyword=video.video_id
+ ".zh-Hans",
extend=options.get(
'subtitlesformat',
None))
if (subtitle_cn_filepath.__len__()) == 1:
# 从list中把唯一的一个数据pop出来
video.subtitle_cn = subtitle_cn_filepath.pop()
result.append(video.subtitle_en)
video.save()
if result == []:
result = False
return result
def download_subtitle(video_id):
"""
下载video的中英字幕并保存到video model中
:param video_id:
:return:
"""
video = Video.objects.get(video_id=video_id)
options = {
'outtmpl': YOUTUBE_DOWNLOAD_DIR + '\%(title)s-%(id)s.%(ext)s',
# name the file the ID of the video
'verbose': True, # Print various debugging information
'restrictfilenames': True,
'subtitleslangs': ['en', 'zh-Hans'], # 要写成list的形式
# 'convertsubtitles': 'srt',
'subtitlesformat': 'vtt',
'writeautomaticsub': True, # 下载字幕，这里的字幕是youtube自动生成的CC字幕
'skip_download': True,
}
with youtube_dl.YoutubeDL(options) as ydl:
ydl.download([video.youtube_url])
# 只适用于subtitlesformat设置为srt或ass的情况，设置为best则失效
# 字幕名称格式 LG K10 and K7 hands-on-_9coAtC2PZI.en.srt
subtitle_en_filepath = search_keyword_in_file(
dir=YOUTUBE_DOWNLOAD_DIR,
keyword=video.video_id + ".en",
extend=options.get('subtitlesformat', None))
result = []
if (subtitle_en_filepath.__len__()) == 1:
# 从list中把唯一的一个数据pop出来
video.subtitle_en = subtitle_en_filepath.pop()
result.append(video.subtitle_en)
subtitle_cn_filepath = search_keyword_in_file(
dir=YOUTUBE_DOWNLOAD_DIR,
keyword=video.video_id + ".zh-Hans",
extend=options.get('subtitlesformat', None))
if (subtitle_cn_filepath.__len__()) == 1:
# 从list中把唯一的一个数据pop出来
video.subtitle_cn = subtitle_cn_filepath.pop()
result.append(video.subtitle_en)
video.save()
if result == []:
result = False
return result
def search_subtitles_file(video_id, subtitle_format):
"""
要自己查看下载目录下是否有相关video id的字幕文件
入存在并将视频文件的地址保存到对应的字段
:param video_id:
:param subtitle_format:vtt, ass
:return:
"""
# 只能查找到一个这样的文件才对
# if (filepath.__len__()) == 1:
# # 从list中把唯一的一个数据pop出来
# subtitle_filepath = filepath.pop()
# return subtitle_filepath
# else:
# return False
video = Video.objects.get(video_id=video_id)
subtitle_en_filepath = search_keyword_in_file(dir=YOUTUBE_DOWNLOAD_DIR,
keyword=video_id +
".en",
extend=subtitle_format)
result = []
if (subtitle_en_filepath.__len__()) > 0:
# 从list中把唯一的一个数据pop出来
video.subtitle_en = subtitle_en_filepath.pop()
result.append(video.subtitle_en.path)
subtitle_cn_filepath = search_keyword_in_file(dir=YOUTUBE_DOWNLOAD_DIR,
keyword=video_id
+ ".zh-Hans",
extend=subtitle_format)
if (subtitle_cn_filepath.__len__()) > 0:
# 从list中把唯一的一个数据pop出来
video.subtitle_cn = subtitle_cn_filepath.pop()
result.append(video.subtitle_cn.path)
video.save(update_fields=["subtitle_en", "subtitle_cn"])
if result == []:
result = False
else:
return result
def search_subtitles_file(video_id, subtitle_format):
"""
要自己查看下载目录下是否有相关video id的字幕文件
入存在并将视频文件的地址保存到对应的字段
:param video_id:
:param subtitle_format:vtt, ass
:return:
"""
# 只能查找到一个这样的文件才对
# if (filepath.__len__()) == 1:
# # 从list中把唯一的一个数据pop出来
# subtitle_filepath = filepath.pop()
# return subtitle_filepath
# else:
# return False
video = Video.objects.get(video_id=video_id)
subtitle_en_filepath = search_keyword_in_file(dir=YOUTUBE_DOWNLOAD_DIR,
keyword=video_id + ".en",
extend=subtitle_format)
result = []
if (subtitle_en_filepath.__len__()) > 0:
# 从list中把唯一的一个数据pop出来
video.subtitle_en = subtitle_en_filepath.pop()
result.append(video.subtitle_en.path)
subtitle_cn_filepath = search_keyword_in_file(dir=YOUTUBE_DOWNLOAD_DIR,
keyword=video_id +
".zh-Hans",
extend=subtitle_format)
if (subtitle_cn_filepath.__len__()) > 0:
# 从list中把唯一的一个数据pop出来
video.subtitle_cn = subtitle_cn_filepath.pop()
result.append(video.subtitle_cn.path)
video.save(update_fields=["subtitle_en", "subtitle_cn"])
if result == []:
return False
else:
return result
def search_video_file(video_id, file_extend):
# 要自己查看下载目录下是否有相关video id的视频、字幕文件
# 入存在并将视频文件的地址保存到对应的字段
video = Video.objects.get(video_id=video_id)
video_filepath = search_keyword_in_file(dir=YOUTUBE_DOWNLOAD_DIR,
keyword=video.video_id,
extend=file_extend)
# 只能查找到一个这样的文件才对
if (video_filepath.__len__()) == 1:
# 从list中把唯一的一个数据pop出来
video.file = video_filepath.pop()
video.save()
return video_filepath
else:
# 找到多个文件，暂时返回False
return False
def download_single_youtube_video_main(video_id):
"""
下载单个youtube视频，并将下载后的视频文件的目录保存到Video.file
:param video_id:
:return:
"""
video = Video.objects.get(video_id=video_id)
# 代码参考 https://github.com/rg3/youtube-dl/blob/master/README.md#embedding
# -youtube-dl
# 参数 https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL
# .py#L121-L269
# 参考 http://willdrevo.com/downloading-youtube-and-soundcloud-audio-with
# -python-and-pandas/
# 支持参数列表 https://github.com/rg3/youtube-dl/blob/master/youtube_dl/options.py
options = {
# 'format': '160+250', # 质量最低的视频，可以节约带宽，用于测试
# 'format': '137+140', # 质量最高的视频，且上传到优酷有声音
'format': 'bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best',
# 'format': 'bestvideo+bestaudio/best',
# 'extractaudio': True, # only keep the audio
# 'audioformat': "mp3", # convert to mp3
'outtmpl': YOUTUBE_DOWNLOAD_DIR + '\%(title)s-%(id)s.%(ext)s',
# name the file the ID of the video
'restrictfilenames': True,
'noplaylist': True, # only download single song, not playlist
'verbose': True, # Print various debugging information
# 'subtitleslangs': ['zh-Hans', 'en'], # 要写成list的形式
# 'subtitlesformat': 'srt',
# 'writeautomaticsub': True, # 下载字幕，这里的字幕是youtube自动生成的CC字幕
# 'embedsubtitles': False, # Embed subtitles in the video (only for
# mkv and mp4 videos
'merge_output_format': 'mkv',
'prefer_ffmpeg': True,
'ffmpeg_location': "E:\\Program Files\\ffmpeg\\bin"
# 'progress_hooks': [my_hook],
}
with youtube_dl.YoutubeDL(options) as ydl:
# youtube_url = video.youtube_url
# 用设置成list的形式
ydl.download([video.youtube_url])
# youtube-dl下载成功后并不会返回下载视频文件的信息
# todo 所以要自己查看下载目录下是否有相关video id的视频，以此来判断是否下载成功
# 并将视频文件的地址保存到对应的字段
video_filepath = search_keyword_in_file(dir=YOUTUBE_DOWNLOAD_DIR,
keyword=video.video_id,
extend=options.get(
'merge_output_format',
None))
# 只能查找到一个这样的文件才对
if (video_filepath.__len__()) == 1:
# 从list中把唯一的一个数据pop出来
video.file = video_filepath.pop()
# 只适用于subtitlesformat设置为srt或ass的情况，设置为best则失效
# 字幕名称格式 LG K10 and K7 hands-on-_9coAtC2PZI.en.srt
# subtitle_en_filepath = search_keyword_in_file(
# dir=YOUTUBE_DOWNLOAD_DIR,
# keyword=video.video_id
# + ".en",
# extend=options.get(
# 'subtitlesformat',
# None))
video.save()
return video_filepath
def download_single_youtube_video_main(video_id):
"""
下载单个youtube视频，并将下载后的视频文件的目录保存到Video.file
:param video_id:
:return:
"""
video = Video.objects.get(video_id=video_id)
# 代码参考 https://github.com/rg3/youtube-dl/blob/master/README.md#embedding
# -youtube-dl
# 参数 https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL
# .py#L121-L269
# 参考 http://willdrevo.com/downloading-youtube-and-soundcloud-audio-with
# -python-and-pandas/
# 支持参数列表 https://github.com/rg3/youtube-dl/blob/master/youtube_dl/options.py
options = {
# 'format': '160+250', # 质量最低的视频，可以节约带宽，用于测试
# 'format': '137+140', # 质量最高的视频，且上传到优酷有声音
'format': 'bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best',
# 'format': 'bestvideo+bestaudio/best',
# 'extractaudio': True, # only keep the audio
# 'audioformat': "mp3", # convert to mp3
'outtmpl': YOUTUBE_DOWNLOAD_DIR + '\%(title)s-%(id)s.%(ext)s',
# name the file the ID of the video
'restrictfilenames': True,
'noplaylist': True, # only download single song, not playlist
'verbose': True, # Print various debugging information
# 'subtitleslangs': ['zh-Hans', 'en'], # 要写成list的形式
# 'subtitlesformat': 'srt',
# 'writeautomaticsub': True, # 下载字幕，这里的字幕是youtube自动生成的CC字幕
# 'embedsubtitles': False, # Embed subtitles in the video (only for
# mkv and mp4 videos
'merge_output_format': 'mkv',
'prefer_ffmpeg': True,
'ffmpeg_location': "E:\\Program Files\\ffmpeg\\bin"
# 'progress_hooks': [my_hook],
}
with youtube_dl.YoutubeDL(options) as ydl:
# youtube_url = video.youtube_url
# 用设置成list的形式
ydl.download([video.youtube_url])
# youtube-dl下载成功后并不会返回下载视频文件的信息
# todo 所以要自己查看下载目录下是否有相关video id的视频，以此来判断是否下载成功
# 并将视频文件的地址保存到对应的字段
video_filepath = search_keyword_in_file(dir=YOUTUBE_DOWNLOAD_DIR,
keyword=video.video_id,
extend=options.get(
'merge_output_format',
None))
# 只能查找到一个这样的文件才对
if (video_filepath.__len__()) == 1:
# 从list中把唯一的一个数据pop出来
video.file = video_filepath.pop()
# 只适用于subtitlesformat设置为srt或ass的情况，设置为best则失效
# 字幕名称格式 LG K10 and K7 hands-on-_9coAtC2PZI.en.srt
# subtitle_en_filepath = search_keyword_in_file(
# dir=YOUTUBE_DOWNLOAD_DIR,
# keyword=video.video_id
# + ".en",
# extend=options.get(
# 'subtitlesformat',
# None))
video.save()
return video_filepath
