mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-12-25 12:45:51 +01:00
[HiDive] Fix extractor (#958)
Closes #952, #408 Authored by: Ashish0804
This commit is contained in:
parent
92790da2bb
commit
a8cb7eca61
@ -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,
|
||||||
)
|
)
|
||||||
@ -57,48 +58,51 @@ 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)
|
||||||
settings = self._download_json(
|
data_videos = re.findall(r'data-video=\"([^\"]+)\"\s?data-captions=\"([^\"]+)\"', webpage)
|
||||||
'https://www.hidive.com/play/settings', video_id,
|
|
||||||
data=urlencode_postdata({
|
|
||||||
'Title': title,
|
|
||||||
'Key': key,
|
|
||||||
'PlayerId': 'f4f895ce1ca713ba263b91caeb1daa2d08904783',
|
|
||||||
}))
|
|
||||||
|
|
||||||
restriction = settings.get('restrictionReason')
|
|
||||||
if restriction == 'RegionRestricted':
|
|
||||||
self.raise_geo_restricted()
|
|
||||||
|
|
||||||
if restriction and restriction != 'None':
|
|
||||||
raise ExtractorError(
|
|
||||||
'%s said: %s' % (self.IE_NAME, restriction), expected=True)
|
|
||||||
|
|
||||||
formats = []
|
formats = []
|
||||||
subtitles = {}
|
subtitles = {}
|
||||||
for rendition_id, rendition in settings['renditions'].items():
|
for data_video in data_videos:
|
||||||
bitrates = rendition.get('bitrates')
|
_, _, _, version, audio, _, extra = data_video[0].split('_')
|
||||||
if not isinstance(bitrates, dict):
|
caption = data_video[1]
|
||||||
continue
|
|
||||||
m3u8_url = url_or_none(bitrates.get('hls'))
|
settings = self._download_json(
|
||||||
if not m3u8_url:
|
'https://www.hidive.com/play/settings', video_id,
|
||||||
continue
|
data=urlencode_postdata({
|
||||||
formats.extend(self._extract_m3u8_formats(
|
'Title': title,
|
||||||
m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
|
'Key': key,
|
||||||
m3u8_id='%s-hls' % rendition_id, fatal=False))
|
'PlayerId': 'f4f895ce1ca713ba263b91caeb1daa2d08904783',
|
||||||
cc_files = rendition.get('ccFiles')
|
'Version': version,
|
||||||
if not isinstance(cc_files, list):
|
'Audio': audio,
|
||||||
continue
|
'Captions': caption,
|
||||||
for cc_file in cc_files:
|
'Extra': extra,
|
||||||
if not isinstance(cc_file, list) or len(cc_file) < 3:
|
}))
|
||||||
|
|
||||||
|
restriction = settings.get('restrictionReason')
|
||||||
|
if restriction == 'RegionRestricted':
|
||||||
|
self.raise_geo_restricted()
|
||||||
|
|
||||||
|
if restriction and restriction != 'None':
|
||||||
|
raise ExtractorError(
|
||||||
|
'%s said: %s' % (self.IE_NAME, restriction), expected=True)
|
||||||
|
|
||||||
|
for rendition_id, rendition in settings['renditions'].items():
|
||||||
|
m3u8_url = url_or_none(try_get(rendition, lambda x: x['bitrates']['hls']))
|
||||||
|
if not m3u8_url:
|
||||||
continue
|
continue
|
||||||
cc_lang = cc_file[0]
|
frmt = self._extract_m3u8_formats(
|
||||||
cc_url = url_or_none(cc_file[2])
|
m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
|
||||||
if not isinstance(cc_lang, compat_str) or not cc_url:
|
m3u8_id='%s-%s-%s-%s' % (version, audio, extra, caption), fatal=False)
|
||||||
continue
|
for f in frmt:
|
||||||
subtitles.setdefault(cc_lang, []).append({
|
f['language'] = audio
|
||||||
'url': cc_url,
|
formats.extend(frmt)
|
||||||
})
|
|
||||||
|
for cc_file in rendition.get('ccFiles', []):
|
||||||
|
cc_url = url_or_none(try_get(cc_file, lambda x: x[2]))
|
||||||
|
# name is used since we cant distinguish subs with same language code
|
||||||
|
cc_lang = try_get(cc_file, (lambda x: x[1].replace(' ', '-').lower(), lambda x: x[0]), str)
|
||||||
|
if cc_url and cc_lang:
|
||||||
|
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}
|
||||||
}
|
}
|
||||||
|
Loading…
Reference in New Issue
Block a user