[hotstar:playlist] Fix issues and improve (closes #12465)

This commit is contained in:
Sergey M․ 2017-11-05 19:14:48 +07:00
parent 477c97f86b
commit 909191de91
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D

View File

@ -1,18 +1,41 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
ExtractorError,
determine_ext,
int_or_none,
)
import re import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
)
class HotStarIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?hotstar\.com/(?:.+?[/-])?(?P<id>\d{10})' class HotStarBaseIE(InfoExtractor):
_GEO_COUNTRIES = ['IN'] _GEO_COUNTRIES = ['IN']
def _download_json(self, *args, **kwargs):
response = super(HotStarBaseIE, self)._download_json(*args, **kwargs)
if response['resultCode'] != 'OK':
if kwargs.get('fatal'):
raise ExtractorError(
response['errorDescription'], expected=True)
return None
return response['resultObj']
def _download_content_info(self, content_id):
return self._download_json(
'https://account.hotstar.com/AVS/besc', content_id, query={
'action': 'GetAggregatedContentDetails',
'appVersion': '5.0.40',
'channel': 'PCTV',
'contentId': content_id,
})['contentInfo'][0]
class HotStarIE(HotStarBaseIE):
_VALID_URL = r'https?://(?:www\.)?hotstar\.com/(?:.+?[/-])?(?P<id>\d{10})'
_TESTS = [{ _TESTS = [{
'url': 'http://www.hotstar.com/on-air-with-aib--english-1000076273', 'url': 'http://www.hotstar.com/on-air-with-aib--english-1000076273',
'info_dict': { 'info_dict': {
@ -36,23 +59,11 @@ class HotStarIE(InfoExtractor):
'only_matching': True, 'only_matching': True,
}] }]
def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', fatal=True, query=None):
json_data = super(HotStarIE, self)._download_json(
url_or_request, video_id, note, fatal=fatal, query=query)
if json_data['resultCode'] != 'OK':
if fatal:
raise ExtractorError(json_data['errorDescription'])
return None
return json_data['resultObj']
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
video_data = self._download_json(
'http://account.hotstar.com/AVS/besc', video_id, query={ video_data = self._download_content_info(video_id)
'action': 'GetAggregatedContentDetails',
'channel': 'PCTV',
'contentId': video_id,
})['contentInfo'][0]
title = video_data['episodeTitle'] title = video_data['episodeTitle']
if video_data.get('encrypted') == 'Y': if video_data.get('encrypted') == 'Y':
@ -103,56 +114,49 @@ class HotStarIE(InfoExtractor):
} }
class HotStarPlaylistIE(InfoExtractor): class HotStarPlaylistIE(HotStarBaseIE):
IE_NAME = 'hotstar:playlist' IE_NAME = 'hotstar:playlist'
_VALID_URL = r'https?://(?:www\.)?hotstar\.com/tv/(?P<playlist_title>.+)/(?P<series_id>\d+)/episodes/(?P<playlist_id>\d{1,})' _VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com/tv/[^/]+/(?P<content_id>\d+))/(?P<type>[^/]+)/(?P<id>\d+)'
_TESTS = [{ _TESTS = [{
'url': 'http://www.hotstar.com/tv/pow-bandi-yuddh-ke/10999/episodes/10856/9993', 'url': 'http://www.hotstar.com/tv/pratidaan/14982/episodes/14812/9993',
'info_dict': { 'info_dict': {
'id': '10856', 'id': '14812',
'title': 'pow-bandi-yuddh-ke',
}, },
'playlist_mincount': 0, 'playlist_mincount': 75,
}, { }, {
'url': 'http://www.hotstar.com/tv/pow-bandi-yuddh-ke/10999/episodes/10856/9993', 'url': 'http://www.hotstar.com/tv/pratidaan/14982/popular-clips/9998/9998',
'only_matching': True, 'only_matching': True,
}] }]
_ITEM_TYPES = {
def _extract_episode_info(self, series_id, playlist_title, video): 'episodes': 'EPISODE',
'popular-clips': 'CLIPS',
picture_url = video.get('urlPictures') }
thumbnail = ''
if picture_url:
thumbnail = 'http://media0-starag.startv.in/r1/thumbs/PCTV/%s/%s/PCTV-%s-hs.jpg' % (picture_url[-2:], picture_url, picture_url)
episode_title = video.get('episodeTitle', '')
episode_title = episode_title.lower().replace(' ', '-')
url = "http://www.hotstar.com/tv/%s/%s/%s/%s" % (playlist_title, series_id, episode_title, video.get('contentId'))
info_dict = {
'id': video.get('contentId'),
'title': video.get('episodeTitle'),
'description': video.get('longDescription'),
'thumbnail': thumbnail,
'url': url,
'_type': 'url',
}
return info_dict
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
series_id = mobj.group('series_id') base_url = mobj.group('url')
playlist_id = mobj.group('playlist_id') content_id = mobj.group('content_id')
playlist_title = mobj.group('playlist_title') playlist_type = mobj.group('type')
content_info = self._download_content_info(content_id)
playlist_id = compat_str(content_info['categoryId'])
collection = self._download_json( collection = self._download_json(
"http://search.hotstar.com/AVS/besc?action=SearchContents&appVersion=5.0.39&channel=PCTV&moreFilters=series:%s;&query=*&searchOrder=last_broadcast_date+desc,year+asc,title+asc&type=EPISODE" % playlist_id, 'https://search.hotstar.com/AVS/besc', playlist_id, query={
playlist_id 'action': 'SearchContents',
) 'appVersion': '5.0.40',
'channel': 'PCTV',
'moreFilters': 'series:%s;' % playlist_id,
'query': '*',
'searchOrder': 'last_broadcast_date desc,year desc,title asc',
'type': self._ITEM_TYPES.get(playlist_type, 'EPISODE'),
})
videos = collection.get('resultObj', {}).get('response', {}).get('docs', [])
entries = [ entries = [
self._extract_episode_info(series_id, playlist_title, video) self.url_result(
for video in videos if video.get('contentId')] '%s/_/%s' % (base_url, video['contentId']),
return self.playlist_result(entries, playlist_id, playlist_title) ie=HotStarIE.ie_key(), video_id=video['contentId'])
for video in collection['response']['docs']
if video.get('contentId')]
return self.playlist_result(entries, playlist_id)