fenix
/
ytdl-nightly
mirror of https://github.com/ytdl-org/ytdl-nightly.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[abc] fix ABC IView extraction and add support for livestreams(closes #16704)(closes #12354)

This commit is contained in:
Remita Amine 2018-06-12 13:07:20 +01:00
parent 5d6c81b63f
commit e0671819e7
1 changed files with 22 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
youtube_dl/extractor/abc.py
View File

@ -105,22 +105,22 @@ class ABCIE(InfoExtractor):
class ABCIViewIE(InfoExtractor): class ABCIViewIE(InfoExtractor):
IE_NAME = 'abc.net.au:iview' IE_NAME = 'abc.net.au:iview'
_VALID_URL = r'https?://iview\.abc\.net\.au/programs/[^/]+/(?P<id>[^/?#]+)' _VALID_URL = r'https?://iview\.abc\.net\.au/(?:[^/]+/)*video/(?P<id>[^/?#]+)'
_GEO_COUNTRIES = ['AU'] _GEO_COUNTRIES = ['AU']
# ABC iview programs are normally available for 14 days only. # ABC iview programs are normally available for 14 days only.
_TESTS = [{ _TESTS = [{
'url': 'https://iview.abc.net.au/programs/ben-and-hollys-little-kingdom/ZY9247A021S00', 'url': 'https://iview.abc.net.au/show/ben-and-hollys-little-kingdom/series/0/video/ZX9371A050S00',
'md5': 'cde42d728b3b7c2b32b1b94b4a548afc', 'md5': 'cde42d728b3b7c2b32b1b94b4a548afc',
'info_dict': { 'info_dict': {
'id': 'ZY9247A021S00', 'id': 'ZX9371A050S00',
'ext': 'mp4', 'ext': 'mp4',
'title': "Gaston's Visit", 'title': "Gaston's Birthday",
'series': "Ben And Holly's Little Kingdom", 'series': "Ben And Holly's Little Kingdom",
'description': 'md5:18db170ad71cf161e006a4c688e33155', 'description': 'md5:f9de914d02f226968f598ac76f105bcf',
'upload_date': '20180318', 'upload_date': '20180604',
'uploader_id': 'abc4kids', 'uploader_id': 'abc4kids',
'timestamp': 1521400959, 'timestamp': 1528140219,
}, },
'params': { 'params': {
'skip_download': True, 'skip_download': True,
@ -129,17 +129,16 @@ class ABCIViewIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) video_params = self._download_json(
video_params = self._parse_json(self._search_regex( 'https://iview.abc.net.au/api/programs/' + video_id, video_id)
r'videoParams\s*=\s*({.+?});', webpage, 'video params'), video_id) title = unescapeHTML(video_params.get('title') or video_params['seriesTitle'])
title = video_params.get('title') or video_params['seriesTitle'] stream = next(s for s in video_params['playlist'] if s.get('type') in ('program', 'livestream'))
stream = next(s for s in video_params['playlist'] if s.get('type') == 'program')
house_number = video_params.get('episodeHouseNumber') house_number = video_params.get('episodeHouseNumber') or video_id
path = '/auth/hls/sign?ts={0}&hn={1}&d=android-mobile'.format( path = '/auth/hls/sign?ts={0}&hn={1}&d=android-tablet'.format(
int(time.time()), house_number) int(time.time()), house_number)
sig = hmac.new( sig = hmac.new(
'android.content.res.Resources'.encode('utf-8'), b'android.content.res.Resources',
path.encode('utf-8'), hashlib.sha256).hexdigest() path.encode('utf-8'), hashlib.sha256).hexdigest()
token = self._download_webpage( token = self._download_webpage(
'http://iview.abc.net.au{0}&sig={1}'.format(path, sig), video_id) 'http://iview.abc.net.au{0}&sig={1}'.format(path, sig), video_id)
@ -169,18 +168,21 @@ class ABCIViewIE(InfoExtractor):
'ext': 'vtt', 'ext': 'vtt',
}] }]
is_live = video_params.get('livestream') == '1'
if is_live:
title = self._live_title(title)
return { return {
'id': video_id, 'id': video_id,
'title': unescapeHTML(title), 'title': title,
'description': self._html_search_meta(['og:description', 'twitter:description'], webpage), 'description': video_params.get('description'),
'thumbnail': self._html_search_meta(['og:image', 'twitter:image:src'], webpage), 'thumbnail': video_params.get('thumbnail'),
'duration': int_or_none(video_params.get('eventDuration')), 'duration': int_or_none(video_params.get('eventDuration')),
'timestamp': parse_iso8601(video_params.get('pubDate'), ' '), 'timestamp': parse_iso8601(video_params.get('pubDate'), ' '),
'series': unescapeHTML(video_params.get('seriesTitle')), 'series': unescapeHTML(video_params.get('seriesTitle')),
'series_id': video_params.get('seriesHouseNumber') or video_id[:7], 'series_id': video_params.get('seriesHouseNumber') or video_id[:7],
'episode_number': int_or_none(self._html_search_meta('episodeNumber', webpage, default=None)),
'episode': self._html_search_meta('episode_title', webpage, default=None),
'uploader_id': video_params.get('channel'), 'uploader_id': video_params.get('channel'),
'formats': formats, 'formats': formats,
'subtitles': subtitles, 'subtitles': subtitles,
'is_live': is_live,
} }