MarcoBuster/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-25 20:55:52 +01:00
Code Issues Projects Releases Wiki Activity

[HiDive] Fix extractor (#958)

Browse Source 
Closes #952, #408
Authored by: Ashish0804
This commit is contained in:
Ashish Gupta 2021-09-15 07:34:54 +05:30 committed by GitHub
parent 92790da2bb
commit a8cb7eca61
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 45 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
yt_dlp/extractor/hidive.py
View File

@ -1,12 +1,13 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_str
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
try_get,
url_or_none, url_or_none,
urlencode_postdata, urlencode_postdata,
) )
@ -57,6 +58,13 @@ def _real_extract(self, url):
mobj = self._match_valid_url(url) mobj = self._match_valid_url(url)
title, key = mobj.group('title', 'key') title, key = mobj.group('title', 'key')
video_id = '%s/%s' % (title, key) video_id = '%s/%s' % (title, key)
webpage = self._download_webpage(url, video_id, fatal=False)
data_videos = re.findall(r'data-video=\"([^\"]+)\"\s?data-captions=\"([^\"]+)\"', webpage)
formats = []
subtitles = {}
for data_video in data_videos:
_, _, _, version, audio, _, extra = data_video[0].split('_')
caption = data_video[1]
settings = self._download_json( settings = self._download_json(
'https://www.hidive.com/play/settings', video_id, 'https://www.hidive.com/play/settings', video_id,
@ -64,6 +72,10 @@ def _real_extract(self, url):
'Title': title, 'Title': title,
'Key': key, 'Key': key,
'PlayerId': 'f4f895ce1ca713ba263b91caeb1daa2d08904783', 'PlayerId': 'f4f895ce1ca713ba263b91caeb1daa2d08904783',
'Version': version,
'Audio': audio,
'Captions': caption,
'Extra': extra,
})) }))
restriction = settings.get('restrictionReason') restriction = settings.get('restrictionReason')
@ -74,31 +86,23 @@ def _real_extract(self, url):
raise ExtractorError( raise ExtractorError(
'%s said: %s' % (self.IE_NAME, restriction), expected=True) '%s said: %s' % (self.IE_NAME, restriction), expected=True)
formats = []
subtitles = {}
for rendition_id, rendition in settings['renditions'].items(): for rendition_id, rendition in settings['renditions'].items():
bitrates = rendition.get('bitrates') m3u8_url = url_or_none(try_get(rendition, lambda x: x['bitrates']['hls']))
if not isinstance(bitrates, dict):
continue
m3u8_url = url_or_none(bitrates.get('hls'))
if not m3u8_url: if not m3u8_url:
continue continue
formats.extend(self._extract_m3u8_formats( frmt = self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='%s-hls' % rendition_id, fatal=False)) m3u8_id='%s-%s-%s-%s' % (version, audio, extra, caption), fatal=False)
cc_files = rendition.get('ccFiles') for f in frmt:
if not isinstance(cc_files, list): f['language'] = audio
continue formats.extend(frmt)
for cc_file in cc_files:
if not isinstance(cc_file, list) or len(cc_file) < 3: for cc_file in rendition.get('ccFiles', []):
continue cc_url = url_or_none(try_get(cc_file, lambda x: x[2]))
cc_lang = cc_file[0] # name is used since we cant distinguish subs with same language code
cc_url = url_or_none(cc_file[2]) cc_lang = try_get(cc_file, (lambda x: x[1].replace(' ', '-').lower(), lambda x: x[0]), str)
if not isinstance(cc_lang, compat_str) or not cc_url: if cc_url and cc_lang:
continue subtitles.setdefault(cc_lang, []).append({'url': cc_url})
subtitles.setdefault(cc_lang, []).append({
'url': cc_url,
})
self._sort_formats(formats) self._sort_formats(formats)
season_number = int_or_none(self._search_regex( season_number = int_or_none(self._search_regex(
@ -114,4 +118,5 @@ def _real_extract(self, url):
'series': title, 'series': title,
'season_number': season_number, 'season_number': season_number,
'episode_number': episode_number, 'episode_number': episode_number,
'http_headers': {'Referer': url}
} }