Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2025-02-16 17:07:54 +01:00
Code Issues Releases Wiki Activity

download subtitles for mewatch.sg

Browse Source
This commit is contained in:
Huey 2020-07-05 12:51:24 +08:00
parent 07af16b92e
commit cfe81de220
No known key found for this signature in database
GPG Key ID: 54C82E718C137231
1 changed files with 120 additions and 89 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

209
youtube_dl/extractor/toggle.py
View File

@ -4,15 +4,10 @@ from __future__ import unicode_literals
import json import json
import re import re
from ..utils import (ExtractorError, determine_ext, error_to_compat_str,
float_or_none, int_or_none, parse_iso8601,
sanitized_Request)
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
determine_ext,
ExtractorError,
float_or_none,
int_or_none,
parse_iso8601,
sanitized_Request,
)
class ToggleIE(InfoExtractor): class ToggleIE(InfoExtractor):
@ -93,7 +88,29 @@ class ToggleIE(InfoExtractor):
_API_USER = 'tvpapi_147' _API_USER = 'tvpapi_147'
_API_PASS = '11111' _API_PASS = '11111'
def _real_extract(self, url): def _get_subtitles(self, video_id):
req = sanitized_Request(
'https://sub.toggle.sg/toggle_api/v1.0/apiService/getSubtitleFilesForMedia?mediaId={0}'.format(video_id),
)
subFiles = self._download_json(req, video_id, 'Downloading subtitles json').get('subtitleFiles', [])
subtitles = dict()
if len(subFiles) == 0:
return {}
for sub in subFiles:
url = sub.get('subtitleFileUrl')
if url is not None:
subtitles.setdefault(sub.get('subtitleFileLanguage'), []).append(dict(
url=url,
ext=re.search(
r'\.(\w{3,4})$',
url
).group(1)
))
return subtitles
def _real_extract(self, url, api_url='https://tvpapi-as.ott.kaltura.com/v3_9/gateways/jsonpostgw.aspx?m=GetMediaInfo'):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage( webpage = self._download_webpage(
@ -125,89 +142,103 @@ class ToggleIE(InfoExtractor):
'mediaType': 0, 'mediaType': 0,
} }
req = sanitized_Request( try:
'http://tvpapi.as.tvinci.com/v2_9/gateways/jsonpostgw.aspx?m=GetMediaInfo', req = sanitized_Request(
json.dumps(params).encode('utf-8')) api_url,
info = self._download_json(req, video_id, 'Downloading video info json') json.dumps(params).encode('utf-8')
)
info = self._download_json(req, video_id, 'Downloading video info json')
title = info['MediaName'] title = info['MediaName']
formats = [] formats = []
for video_file in info.get('Files', []): for video_file in info.get('Files', []):
video_url, vid_format = video_file.get('URL'), video_file.get('Format') video_url, vid_format = video_file.get('URL'), video_file.get('Format')
if not video_url or video_url == 'NA' or not vid_format: if not video_url or video_url == 'NA' or not vid_format:
continue continue
ext = determine_ext(video_url) ext = determine_ext(video_url)
vid_format = vid_format.replace(' ', '') vid_format = vid_format.replace(' ', '')
# if geo-restricted, m3u8 is inaccessible, but mp4 is okay # if geo-restricted, m3u8 is inaccessible, but mp4 is okay
if ext == 'm3u8': if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats( formats.extend(self._extract_m3u8_formats(
video_url, video_id, ext='mp4', m3u8_id=vid_format, video_url, video_id, ext='mp4', m3u8_id=vid_format,
note='Downloading %s m3u8 information' % vid_format, note='Downloading %s m3u8 information' % vid_format,
errnote='Failed to download %s m3u8 information' % vid_format, errnote='Failed to download %s m3u8 information' % vid_format,
fatal=False)) fatal=False))
elif ext == 'mpd': elif ext == 'mpd':
formats.extend(self._extract_mpd_formats( formats.extend(self._extract_mpd_formats(
video_url, video_id, mpd_id=vid_format, video_url, video_id, mpd_id=vid_format,
note='Downloading %s MPD manifest' % vid_format, note='Downloading %s MPD manifest' % vid_format,
errnote='Failed to download %s MPD manifest' % vid_format, errnote='Failed to download %s MPD manifest' % vid_format,
fatal=False)) fatal=False))
elif ext == 'ism': elif ext == 'ism':
formats.extend(self._extract_ism_formats( formats.extend(self._extract_ism_formats(
video_url, video_id, ism_id=vid_format, video_url, video_id, ism_id=vid_format,
note='Downloading %s ISM manifest' % vid_format, note='Downloading %s ISM manifest' % vid_format,
errnote='Failed to download %s ISM manifest' % vid_format, errnote='Failed to download %s ISM manifest' % vid_format,
fatal=False)) fatal=False))
elif ext in ('mp4', 'wvm'): elif ext in ('mp4', 'wvm'):
# wvm are drm-protected files # wvm are drm-protected files
formats.append({ formats.append({
'ext': ext, 'ext': ext,
'url': video_url, 'url': video_url,
'format_id': vid_format, 'format_id': vid_format,
'preference': self._FORMAT_PREFERENCES.get(ext + '-' + vid_format) or -1, 'preference': self._FORMAT_PREFERENCES.get(ext + '-' + vid_format) or -1,
'format_note': 'DRM-protected video' if ext == 'wvm' else None 'format_note': 'DRM-protected video' if ext == 'wvm' else None
}) })
if not formats: if not formats:
# Most likely because geo-blocked # Most likely because geo-blocked
raise ExtractorError('No downloadable videos found', expected=True) raise ExtractorError('No downloadable videos found', expected=True)
self._sort_formats(formats) self._sort_formats(formats)
duration = int_or_none(info.get('Duration')) duration = int_or_none(info.get('Duration'))
description = info.get('Description') description = info.get('Description')
created_at = parse_iso8601(info.get('CreationDate') or None) created_at = parse_iso8601(info.get('CreationDate') or None)
average_rating = float_or_none(info.get('Rating')) average_rating = float_or_none(info.get('Rating'))
view_count = int_or_none(info.get('ViewCounter') or info.get('view_counter')) view_count = int_or_none(info.get('ViewCounter') or info.get('view_counter'))
like_count = int_or_none(info.get('LikeCounter') or info.get('like_counter')) like_count = int_or_none(info.get('LikeCounter') or info.get('like_counter'))
thumbnails = [] thumbnails = []
for picture in info.get('Pictures', []): for picture in info.get('Pictures', []):
if not isinstance(picture, dict): if not isinstance(picture, dict):
continue continue
pic_url = picture.get('URL') pic_url = picture.get('URL')
if not pic_url: if not pic_url:
continue continue
thumbnail = { thumbnail = {
'url': pic_url, 'url': pic_url,
}
pic_size = picture.get('PicSize', '')
m = re.search(r'(?P<width>\d+)[xX](?P<height>\d+)', pic_size)
if m:
thumbnail.update({
'width': int(m.group('width')),
'height': int(m.group('height')),
})
thumbnails.append(thumbnail)
subtitles = self._get_subtitles(video_id)
return {
'id': video_id,
'title': title,
'description': description,
'duration': duration,
'timestamp': created_at,
'average_rating': average_rating,
'view_count': view_count,
'like_count': like_count,
'thumbnails': thumbnails,
'formats': formats,
'subtitles': subtitles
} }
pic_size = picture.get('PicSize', '') except ExtractorError as err:
m = re.search(r'(?P<width>\d+)[xX](?P<height>\d+)', pic_size) self._downloader.report_warning(
if m: 'Could not get metadata from tvpapi-as.ott.kaltura.com: %s \nTrying tvpapi.as.tvinci.com instead'
thumbnail.update({ % error_to_compat_str(err)
'width': int(m.group('width')), )
'height': int(m.group('height')), self._real_extract(
}) video_id,
thumbnails.append(thumbnail) api_url='http://tvpapi.as.tvinci.com/v2_9/gateways/jsonpostgw.aspx?m=GetMediaInfo'
)
return {
'id': video_id,
'title': title,
'description': description,
'duration': duration,
'timestamp': created_at,
'average_rating': average_rating,
'view_count': view_count,
'like_count': like_count,
'thumbnails': thumbnails,
'formats': formats,
}