commit c7d6f614f35c81cf64941affdf683a478078274b
parent 08a00eef79c8f8b12211513b241404394ef6120c
Author: Remita Amine <remitamine@gmail.com>
Date: Fri, 10 Feb 2017 16:59:49 +0100
[corus] Add new extractor(closes #12060)(#9164)
Diffstat:
4 files changed, 77 insertions(+), 50 deletions(-)
diff --git a/youtube_dl/extractor/corus.py b/youtube_dl/extractor/corus.py
@@ -0,0 +1,72 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .theplatform import ThePlatformFeedIE
+from ..utils import int_or_none
+
+
+class CorusIE(ThePlatformFeedIE):
+ _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:globaltv|etcanada)\.com|(?:hgtv|foodnetwork|slice)\.ca)/(?:video/|(?:[^/]+/)+(?:videos/[a-z0-9-]+-|video\.html\?.*?\bv=))(?P<id>\d+)'
+ _TESTS = [{
+ 'url': 'http://www.hgtv.ca/shows/bryan-inc/videos/movie-night-popcorn-with-bryan-870923331648/',
+ 'md5': '05dcbca777bf1e58c2acbb57168ad3a6',
+ 'info_dict': {
+ 'id': '870923331648',
+ 'ext': 'mp4',
+ 'title': 'Movie Night Popcorn with Bryan',
+ 'description': 'Bryan whips up homemade popcorn, the old fashion way for Jojo and Lincoln.',
+ 'uploader': 'SHWM-NEW',
+ 'upload_date': '20170206',
+ 'timestamp': 1486392197,
+ },
+ }, {
+ 'url': 'http://www.foodnetwork.ca/shows/chopped/video/episode/chocolate-obsession/video.html?v=872683587753',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://etcanada.com/video/873675331955/meet-the-survivor-game-changers-castaways-part-2/',
+ 'only_matching': True,
+ }]
+
+ _TP_FEEDS = {
+ 'globaltv': {
+ 'feed_id': 'ChQqrem0lNUp',
+ 'account_id': 2269680845,
+ },
+ 'etcanada': {
+ 'feed_id': 'ChQqrem0lNUp',
+ 'account_id': 2269680845,
+ },
+ 'hgtv': {
+ 'feed_id': 'L0BMHXi2no43',
+ 'account_id': 2414428465,
+ },
+ 'foodnetwork': {
+ 'feed_id': 'ukK8o58zbRmJ',
+ 'account_id': 2414429569,
+ },
+ 'slice': {
+ 'feed_id': '5tUJLgV2YNJ5',
+ 'account_id': 2414427935,
+ },
+ }
+
+ def _real_extract(self, url):
+ domain, video_id = re.match(self._VALID_URL, url).groups()
+ feed_info = self._TP_FEEDS[domain.split('.')[0]]
+ return self._extract_feed_info('dtjsEC', feed_info['feed_id'], 'byId=' + video_id, video_id, lambda e: {
+ 'episode_number': int_or_none(e.get('pl1$episode')),
+ 'season_number': int_or_none(e.get('pl1$season')),
+ 'series': e.get('pl1$show'),
+ }, {
+ 'HLS': {
+ 'manifest': 'm3u',
+ },
+ 'DesktopHLS Default': {
+ 'manifest': 'm3u',
+ },
+ 'MP4 MBR': {
+ 'manifest': 'm3u',
+ },
+ }, feed_info['account_id'])
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
@@ -202,6 +202,7 @@ from .commonprotocols import (
RtmpIE,
)
from .condenast import CondeNastIE
+from .corus import CorusIE
from .cracked import CrackedIE
from .crackle import CrackleIE
from .criterion import CriterionIE
@@ -381,10 +382,7 @@ from .heise import HeiseIE
from .hellporno import HellPornoIE
from .helsinki import HelsinkiIE
from .hentaistigma import HentaiStigmaIE
-from .hgtv import (
- HGTVIE,
- HGTVComShowIE,
-)
+from .hgtv import HGTVComShowIE
from .historicfilms import HistoricFilmsIE
from .hitbox import HitboxIE, HitboxLiveIE
from .hitrecord import HitRecordIE
diff --git a/youtube_dl/extractor/hgtv.py b/youtube_dl/extractor/hgtv.py
@@ -2,50 +2,6 @@
from __future__ import unicode_literals
from .common import InfoExtractor
-from ..utils import (
- int_or_none,
- js_to_json,
- smuggle_url,
-)
-
-
-class HGTVIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?hgtv\.ca/[^/]+/video/(?P<id>[^/]+)/video.html'
- _TEST = {
- 'url': 'http://www.hgtv.ca/homefree/video/overnight-success/video.html?v=738081859718&p=1&s=da#video',
- 'md5': '',
- 'info_dict': {
- 'id': 'aFH__I_5FBOX',
- 'ext': 'mp4',
- 'title': 'Overnight Success',
- 'description': 'After weeks of hard work, high stakes, breakdowns and pep talks, the final 2 contestants compete to win the ultimate dream.',
- 'uploader': 'SHWM-NEW',
- 'timestamp': 1470320034,
- 'upload_date': '20160804',
- },
- 'params': {
- # m3u8 download
- 'skip_download': True,
- },
- }
-
- def _real_extract(self, url):
- display_id = self._match_id(url)
- webpage = self._download_webpage(url, display_id)
- embed_vars = self._parse_json(self._search_regex(
- r'(?s)embed_vars\s*=\s*({.*?});',
- webpage, 'embed vars'), display_id, js_to_json)
- return {
- '_type': 'url_transparent',
- 'url': smuggle_url(
- 'http://link.theplatform.com/s/dtjsEC/%s?mbr=true&manifest=m3u' % embed_vars['pid'], {
- 'force_smil_url': True
- }),
- 'series': embed_vars.get('show'),
- 'season_number': int_or_none(embed_vars.get('season')),
- 'episode_number': int_or_none(embed_vars.get('episode')),
- 'ie_key': 'ThePlatform',
- }
class HGTVComShowIE(InfoExtractor):
diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py
@@ -306,9 +306,10 @@ class ThePlatformFeedIE(ThePlatformBaseIE):
},
}]
- def _extract_feed_info(self, provider_id, feed_id, filter_query, video_id, custom_fields=None, asset_types_query={}):
+ def _extract_feed_info(self, provider_id, feed_id, filter_query, video_id, custom_fields=None, asset_types_query={}, account_id=None):
real_url = self._URL_TEMPLATE % (self.http_scheme(), provider_id, feed_id, filter_query)
entry = self._download_json(real_url, video_id)['entries'][0]
+ main_smil_url = 'http://link.theplatform.com/s/%s/media/guid/%d/%s' % (provider_id, account_id, entry['guid']) if account_id else None
formats = []
subtitles = {}
@@ -333,7 +334,7 @@ class ThePlatformFeedIE(ThePlatformBaseIE):
if asset_type in asset_types_query:
query.update(asset_types_query[asset_type])
cur_formats, cur_subtitles = self._extract_theplatform_smil(update_url_query(
- smil_url, query), video_id, 'Downloading SMIL data for %s' % asset_type)
+ main_smil_url or smil_url, query), video_id, 'Downloading SMIL data for %s' % asset_type)
formats.extend(cur_formats)
subtitles = self._merge_subtitles(subtitles, cur_subtitles)
