aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/aenetworks.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor/aenetworks.py')
-rw-r--r--youtube_dl/extractor/aenetworks.py206
1 files changed, 162 insertions, 44 deletions
diff --git a/youtube_dl/extractor/aenetworks.py b/youtube_dl/extractor/aenetworks.py
index 1bbfe2641..8f53050c9 100644
--- a/youtube_dl/extractor/aenetworks.py
+++ b/youtube_dl/extractor/aenetworks.py
@@ -2,41 +2,33 @@ from __future__ import unicode_literals
import re
-from .common import InfoExtractor
+from .theplatform import ThePlatformIE
from ..utils import (
smuggle_url,
update_url_query,
unescapeHTML,
+ extract_attributes,
+ get_element_by_attribute,
)
+from ..compat import (
+ compat_urlparse,
+)
+
+class AENetworksBaseIE(ThePlatformIE):
+ _THEPLATFORM_KEY = 'crazyjava'
+ _THEPLATFORM_SECRET = 's3cr3t'
-class AENetworksIE(InfoExtractor):
+
+class AENetworksIE(AENetworksBaseIE):
IE_NAME = 'aenetworks'
IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network'
- _VALID_URL = r'https?://(?:www\.)?(?:(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?P<type>[^/]+)/(?:[^/]+/)+(?P<id>[^/]+?)(?:$|[?#])'
-
+ _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?:shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|movies/(?P<movie_display_id>[^/]+)/full-movie)'
_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',
- 'info_dict': {
- 'id': 'g12m5Gyt3fdR',
- 'ext': 'mp4',
- 'title': "Bet You Didn't Know: Valentine's Day",
- 'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
- 'timestamp': 1375819729,
- 'upload_date': '20130806',
- 'uploader': 'AENE-NEW',
- },
- 'params': {
- # m3u8 download
- 'skip_download': True,
- },
- 'add_ie': ['ThePlatform'],
- 'expected_warnings': ['JSON-LD'],
- }, {
'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
'md5': '8ff93eb073449f151d6b90c0ae1ef0c7',
'info_dict': {
- 'id': 'eg47EERs_JsZ',
+ 'id': '22253814',
'ext': 'mp4',
'title': 'Winter Is Coming',
'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
@@ -46,42 +38,168 @@ class AENetworksIE(InfoExtractor):
},
'add_ie': ['ThePlatform'],
}, {
- 'url': 'http://www.aetv.com/shows/duck-dynasty/video/inlawful-entry',
+ 'url': 'http://www.history.com/shows/ancient-aliens/season-1',
+ 'info_dict': {
+ 'id': '71889446852',
+ },
+ 'playlist_mincount': 5,
+ }, {
+ 'url': 'http://www.mylifetime.com/shows/atlanta-plastic',
+ 'info_dict': {
+ 'id': 'SERIES4317',
+ 'title': 'Atlanta Plastic',
+ },
+ 'playlist_mincount': 2,
+ }, {
+ 'url': 'http://www.aetv.com/shows/duck-dynasty/season-9/episode-1',
'only_matching': True
}, {
- 'url': 'http://www.fyi.tv/shows/tiny-house-nation/videos/207-sq-ft-minnesota-prairie-cottage',
+ 'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8',
'only_matching': True
}, {
- 'url': 'http://www.mylifetime.com/shows/project-runway-junior/video/season-1/episode-6/superstar-clients',
+ 'url': 'http://www.mylifetime.com/shows/project-runway-junior/season-1/episode-6',
+ 'only_matching': True
+ }, {
+ 'url': 'http://www.mylifetime.com/movies/center-stage-on-pointe/full-movie',
'only_matching': True
}]
+ _DOMAIN_TO_REQUESTOR_ID = {
+ 'history.com': 'HISTORY',
+ 'aetv.com': 'AETV',
+ 'mylifetime.com': 'LIFETIME',
+ 'fyi.tv': 'FYI',
+ }
def _real_extract(self, url):
- page_type, video_id = re.match(self._VALID_URL, url).groups()
+ domain, show_path, movie_display_id = re.match(self._VALID_URL, url).groups()
+ display_id = show_path or movie_display_id
+ webpage = self._download_webpage(url, display_id)
+ if show_path:
+ url_parts = show_path.split('/')
+ url_parts_len = len(url_parts)
+ if url_parts_len == 1:
+ entries = []
+ for season_url_path in re.findall(r'(?s)<li[^>]+data-href="(/shows/%s/season-\d+)"' % url_parts[0], webpage):
+ entries.append(self.url_result(
+ compat_urlparse.urljoin(url, season_url_path), 'AENetworks'))
+ return self.playlist_result(
+ entries, self._html_search_meta('aetn:SeriesId', webpage),
+ self._html_search_meta('aetn:SeriesTitle', webpage))
+ elif url_parts_len == 2:
+ entries = []
+ for episode_item in re.findall(r'(?s)<div[^>]+class="[^"]*episode-item[^"]*"[^>]*>', webpage):
+ episode_attributes = extract_attributes(episode_item)
+ episode_url = compat_urlparse.urljoin(
+ url, episode_attributes['data-canonical'])
+ entries.append(self.url_result(
+ episode_url, 'AENetworks',
+ episode_attributes['data-videoid']))
+ return self.playlist_result(
+ entries, self._html_search_meta('aetn:SeasonId', webpage))
+
+ query = {
+ 'mbr': 'true',
+ 'assetTypes': 'medium_video_s3'
+ }
+ video_id = self._html_search_meta('aetn:VideoID', webpage)
+ media_url = self._search_regex(
+ r"media_url\s*=\s*'([^']+)'", webpage, 'video url')
+ theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
+ r'https?://link.theplatform.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
+ info = self._parse_theplatform_metadata(theplatform_metadata)
+ if theplatform_metadata.get('AETN$isBehindWall'):
+ requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain]
+ resource = '<rss version="2.0" xmlns:media="http://search.yahoo.com/mrss/"><channel><title>%s</title><item><title>%s</title><guid>%s</guid><media:rating scheme="urn:v-chip">%s</media:rating></item></channel></rss>' % (requestor_id, theplatform_metadata['title'], theplatform_metadata['AETN$PPL_pplProgramId'], theplatform_metadata['ratings'][0]['rating'])
+ query['auth'] = self._extract_mvpd_auth(
+ url, video_id, requestor_id, resource)
+ info.update(self._search_json_ld(webpage, video_id, fatal=False))
+ media_url = update_url_query(media_url, query)
+ 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
- webpage = self._download_webpage(url, video_id)
- video_url_re = [
- r'data-href="[^"]*/%s"[^>]+data-release-url="([^"]+)"' % video_id,
- r"media_url\s*=\s*'([^']+)'"
- ]
- video_url = unescapeHTML(self._search_regex(video_url_re, webpage, 'video url'))
- query = {'mbr': 'true'}
- if page_type == 'shows':
- query['assetTypes'] = 'medium_video_s3'
- if 'switch=hds' in video_url:
- query['switch'] = 'hls'
+class HistoryTopicIE(AENetworksBaseIE):
+ IE_NAME = 'history:topic'
+ IE_DESC = 'History.com Topic'
+ _VALID_URL = r'https?://(?:www\.)?history\.com/topics/(?:[^/]+/)?(?P<topic_id>[^/]+)(?:/[^/]+(?:/(?P<video_display_id>[^/?#]+))?)?'
+ _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',
+ 'info_dict': {
+ 'id': '40700995724',
+ 'ext': 'mp4',
+ 'title': "Bet You Didn't Know: Valentine's Day",
+ 'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
+ 'timestamp': 1375819729,
+ 'upload_date': '20130806',
+ 'uploader': 'AENE-NEW',
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
+ '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': 24,
+ }, {
+ '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,
+ }]
- info = self._search_json_ld(webpage, video_id, fatal=False)
- info.update({
+ def theplatform_url_result(self, theplatform_url, video_id, query):
+ return {
'_type': 'url_transparent',
+ 'id': video_id,
'url': smuggle_url(
- update_url_query(video_url, query),
+ update_url_query(theplatform_url, query),
{
'sig': {
- 'key': 'crazyjava',
- 'secret': 's3cr3t'},
+ 'key': self._THEPLATFORM_KEY,
+ 'secret': self._THEPLATFORM_SECRET,
+ },
'force_smil_url': True
}),
- })
- return info
+ 'ie_key': 'ThePlatform',
+ }
+
+ def _real_extract(self, url):
+ topic_id, video_display_id = re.match(self._VALID_URL, url).groups()
+ if video_display_id:
+ webpage = self._download_webpage(url, video_display_id)
+ release_url, video_id = re.search(r"_videoPlayer.play\('([^']+)'\s*,\s*'[^']+'\s*,\s*'(\d+)'\)", webpage).groups()
+ release_url = unescapeHTML(release_url)
+
+ return self.theplatform_url_result(
+ release_url, video_id, {
+ 'mbr': 'true',
+ 'switch': 'hls'
+ })
+ else:
+ webpage = self._download_webpage(url, topic_id)
+ entries = []
+ for episode_item in re.findall(r'<a.+?data-release-url="[^"]+"[^>]*>', webpage):
+ 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'
+ }))
+ return self.playlist_result(entries, topic_id, get_element_by_attribute('class', 'show-title', webpage))
generated by cgit v1.2.3 (git 2.26.2) at 2024-08-23 20:21:26 +0000