[aenetworks] fix history topic extraction and extract more formats

This commit is contained in:
Remita Amine 2019-04-14 11:46:33 +01:00
parent 180a9dff1f
commit 4f1e02ad60

View File

@ -4,11 +4,11 @@ import re
from .theplatform import ThePlatformIE from .theplatform import ThePlatformIE
from ..utils import ( from ..utils import (
extract_attributes,
ExtractorError,
int_or_none,
smuggle_url, smuggle_url,
update_url_query, update_url_query,
unescapeHTML,
extract_attributes,
get_element_by_attribute,
) )
from ..compat import ( from ..compat import (
compat_urlparse, compat_urlparse,
@ -19,6 +19,43 @@ class AENetworksBaseIE(ThePlatformIE):
_THEPLATFORM_KEY = 'crazyjava' _THEPLATFORM_KEY = 'crazyjava'
_THEPLATFORM_SECRET = 's3cr3t' _THEPLATFORM_SECRET = 's3cr3t'
def _extract_aen_smil(self, smil_url, video_id, auth=None):
query = {'mbr': 'true'}
if auth:
query['auth'] = auth
TP_SMIL_QUERY = [{
'assetTypes': 'high_video_ak',
'switch': 'hls_high_ak'
}, {
'assetTypes': 'high_video_s3'
}, {
'assetTypes': 'high_video_s3',
'switch': 'hls_ingest_fastly'
}]
formats = []
subtitles = {}
last_e = None
for q in TP_SMIL_QUERY:
q.update(query)
m_url = update_url_query(smil_url, q)
m_url = self._sign_url(m_url, self._THEPLATFORM_KEY, self._THEPLATFORM_SECRET)
try:
tp_formats, tp_subtitles = self._extract_theplatform_smil(
m_url, video_id, 'Downloading %s SMIL data' % (q.get('switch') or q['assetTypes']))
except ExtractorError as e:
last_e = e
continue
formats.extend(tp_formats)
subtitles = self._merge_subtitles(subtitles, tp_subtitles)
if last_e and not formats:
raise last_e
self._sort_formats(formats)
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
}
class AENetworksIE(AENetworksBaseIE): class AENetworksIE(AENetworksBaseIE):
IE_NAME = 'aenetworks' IE_NAME = 'aenetworks'
@ -33,22 +70,25 @@ class AENetworksIE(AENetworksBaseIE):
(?: (?:
shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})| shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|
movies/(?P<movie_display_id>[^/]+)(?:/full-movie)?| movies/(?P<movie_display_id>[^/]+)(?:/full-movie)?|
specials/(?P<special_display_id>[^/]+)/full-special| specials/(?P<special_display_id>[^/]+)/(?:full-special|preview-)|
collections/[^/]+/(?P<collection_display_id>[^/]+) collections/[^/]+/(?P<collection_display_id>[^/]+)
) )
''' '''
_TESTS = [{ _TESTS = [{
'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1', 'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
'md5': 'a97a65f7e823ae10e9244bc5433d5fe6',
'info_dict': { 'info_dict': {
'id': '22253814', 'id': '22253814',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Winter Is Coming', 'title': 'Winter is Coming',
'description': 'md5:641f424b7a19d8e24f26dea22cf59d74', 'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
'timestamp': 1338306241, 'timestamp': 1338306241,
'upload_date': '20120529', 'upload_date': '20120529',
'uploader': 'AENE-NEW', 'uploader': 'AENE-NEW',
}, },
'params': {
# m3u8 download
'skip_download': True,
},
'add_ie': ['ThePlatform'], 'add_ie': ['ThePlatform'],
}, { }, {
'url': 'http://www.history.com/shows/ancient-aliens/season-1', 'url': 'http://www.history.com/shows/ancient-aliens/season-1',
@ -84,6 +124,9 @@ class AENetworksIE(AENetworksBaseIE):
}, { }, {
'url': 'https://www.historyvault.com/collections/america-the-story-of-us/westward', 'url': 'https://www.historyvault.com/collections/america-the-story-of-us/westward',
'only_matching': True 'only_matching': True
}, {
'url': 'https://www.aetv.com/specials/hunting-jonbenets-killer-the-untold-story/preview-hunting-jonbenets-killer-the-untold-story',
'only_matching': True
}] }]
_DOMAIN_TO_REQUESTOR_ID = { _DOMAIN_TO_REQUESTOR_ID = {
'history.com': 'HISTORY', 'history.com': 'HISTORY',
@ -124,11 +167,6 @@ class AENetworksIE(AENetworksBaseIE):
return self.playlist_result( return self.playlist_result(
entries, self._html_search_meta('aetn:SeasonId', webpage)) entries, self._html_search_meta('aetn:SeasonId', webpage))
query = {
'mbr': 'true',
'assetTypes': 'high_video_ak',
'switch': 'hls_high_ak',
}
video_id = self._html_search_meta('aetn:VideoID', webpage) video_id = self._html_search_meta('aetn:VideoID', webpage)
media_url = self._search_regex( media_url = self._search_regex(
[r"media_url\s*=\s*'(?P<url>[^']+)'", [r"media_url\s*=\s*'(?P<url>[^']+)'",
@ -138,64 +176,39 @@ class AENetworksIE(AENetworksBaseIE):
theplatform_metadata = self._download_theplatform_metadata(self._search_regex( theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
r'https?://link\.theplatform\.com/s/([^?]+)', media_url, 'theplatform_path'), video_id) r'https?://link\.theplatform\.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
info = self._parse_theplatform_metadata(theplatform_metadata) info = self._parse_theplatform_metadata(theplatform_metadata)
auth = None
if theplatform_metadata.get('AETN$isBehindWall'): if theplatform_metadata.get('AETN$isBehindWall'):
requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain] requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain]
resource = self._get_mvpd_resource( resource = self._get_mvpd_resource(
requestor_id, theplatform_metadata['title'], requestor_id, theplatform_metadata['title'],
theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'), theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
theplatform_metadata['ratings'][0]['rating']) theplatform_metadata['ratings'][0]['rating'])
query['auth'] = self._extract_mvpd_auth( auth = self._extract_mvpd_auth(
url, video_id, requestor_id, resource) url, video_id, requestor_id, resource)
info.update(self._search_json_ld(webpage, video_id, fatal=False)) info.update(self._search_json_ld(webpage, video_id, fatal=False))
media_url = update_url_query(media_url, query) info.update(self._extract_aen_smil(media_url, video_id, auth))
media_url = self._sign_url(media_url, self._THEPLATFORM_KEY, self._THEPLATFORM_SECRET)
formats, subtitles = self._extract_theplatform_smil(media_url, video_id)
self._sort_formats(formats)
info.update({
'id': video_id,
'formats': formats,
'subtitles': subtitles,
})
return info return info
class HistoryTopicIE(AENetworksBaseIE): class HistoryTopicIE(AENetworksBaseIE):
IE_NAME = 'history:topic' IE_NAME = 'history:topic'
IE_DESC = 'History.com Topic' IE_DESC = 'History.com Topic'
_VALID_URL = r'https?://(?:www\.)?history\.com/topics/(?:[^/]+/)?(?P<topic_id>[^/]+)(?:/[^/]+(?:/(?P<video_display_id>[^/?#]+))?)?' _VALID_URL = r'https?://(?:www\.)?history\.com/topics/[^/]+/(?P<id>[\w+-]+?)-video'
_TESTS = [{ _TESTS = [{
'url': 'http://www.history.com/topics/valentines-day/history-of-valentines-day/videos/bet-you-didnt-know-valentines-day?m=528e394da93ae&s=undefined&f=1&free=false', 'url': 'https://www.history.com/topics/valentines-day/history-of-valentines-day-video',
'info_dict': { 'info_dict': {
'id': '40700995724', 'id': '40700995724',
'ext': 'mp4', 'ext': 'mp4',
'title': "Bet You Didn't Know: Valentine's Day", 'title': "History of Valentines Day",
'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7', 'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
'timestamp': 1375819729, 'timestamp': 1375819729,
'upload_date': '20130806', 'upload_date': '20130806',
'uploader': 'AENE-NEW',
}, },
'params': { 'params': {
# m3u8 download # m3u8 download
'skip_download': True, 'skip_download': True,
}, },
'add_ie': ['ThePlatform'], 'add_ie': ['ThePlatform'],
}, {
'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/videos',
'info_dict':
{
'id': 'world-war-i-history',
'title': 'World War I History',
},
'playlist_mincount': 23,
}, {
'url': 'http://www.history.com/topics/world-war-i-history/videos',
'only_matching': True,
}, {
'url': 'http://www.history.com/topics/world-war-i/world-war-i-history',
'only_matching': True,
}, {
'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/speeches',
'only_matching': True,
}] }]
def theplatform_url_result(self, theplatform_url, video_id, query): def theplatform_url_result(self, theplatform_url, video_id, query):
@ -215,27 +228,19 @@ class HistoryTopicIE(AENetworksBaseIE):
} }
def _real_extract(self, url): def _real_extract(self, url):
topic_id, video_display_id = re.match(self._VALID_URL, url).groups() display_id = self._match_id(url)
if video_display_id: webpage = self._download_webpage(url, display_id)
webpage = self._download_webpage(url, video_display_id) video_id = self._search_regex(
release_url, video_id = re.search(r"_videoPlayer.play\('([^']+)'\s*,\s*'[^']+'\s*,\s*'(\d+)'\)", webpage).groups() r'<phoenix-iframe[^>]+src="[^"]+\btpid=(\d+)', webpage, 'tpid')
release_url = unescapeHTML(release_url) result = self._download_json(
'https://feeds.video.aetnd.com/api/v2/history/videos',
return self.theplatform_url_result( video_id, query={'filter[id]': video_id})['results'][0]
release_url, video_id, { title = result['title']
'mbr': 'true', info = self._extract_aen_smil(result['publicUrl'], video_id)
'switch': 'hls', info.update({
'assetTypes': 'high_video_ak', 'title': title,
}) 'description': result.get('description'),
else: 'duration': int_or_none(result.get('duration')),
webpage = self._download_webpage(url, topic_id) 'timestamp': int_or_none(result.get('added'), 1000),
entries = [] })
for episode_item in re.findall(r'<a.+?data-release-url="[^"]+"[^>]*>', webpage): return info
video_attributes = extract_attributes(episode_item)
entries.append(self.theplatform_url_result(
video_attributes['data-release-url'], video_attributes['data-id'], {
'mbr': 'true',
'switch': 'hls',
'assetTypes': 'high_video_ak',
}))
return self.playlist_result(entries, topic_id, get_element_by_attribute('class', 'show-title', webpage))