Update to ytdl-2021.03.03

This commit is contained in:
pukkandan 2021-03-03 11:19:33 +05:30
parent a5c5623470
commit 3721515bde
No known key found for this signature in database
GPG Key ID: 0F00D95A001F4698
3 changed files with 63 additions and 20 deletions

View File

@ -5,10 +5,15 @@
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import (
compat_etree_Element,
compat_HTTPError,
compat_urlparse,
)
from ..utils import ( from ..utils import (
ExtractorError,
clean_html, clean_html,
dict_get, dict_get,
ExtractorError,
float_or_none, float_or_none,
get_element_by_class, get_element_by_class,
int_or_none, int_or_none,
@ -21,11 +26,6 @@
urlencode_postdata, urlencode_postdata,
urljoin, urljoin,
) )
from ..compat import (
compat_etree_Element,
compat_HTTPError,
compat_urlparse,
)
class BBCCoUkIE(InfoExtractor): class BBCCoUkIE(InfoExtractor):
@ -793,6 +793,20 @@ class BBCIE(BBCCoUkIE):
'description': 'Learn English words and phrases from this story', 'description': 'Learn English words and phrases from this story',
}, },
'add_ie': [BBCCoUkIE.ie_key()], 'add_ie': [BBCCoUkIE.ie_key()],
}, {
# BBC Reel
'url': 'https://www.bbc.com/reel/video/p07c6sb6/how-positive-thinking-is-harming-your-happiness',
'info_dict': {
'id': 'p07c6sb9',
'ext': 'mp4',
'title': 'How positive thinking is harming your happiness',
'alt_title': 'The downsides of positive thinking',
'description': 'md5:fad74b31da60d83b8265954ee42d85b4',
'duration': 235,
'thumbnail': r're:https?://.+/p07c9dsr.jpg',
'upload_date': '20190604',
'categories': ['Psychology'],
},
}] }]
@classmethod @classmethod
@ -929,7 +943,7 @@ def _real_extract(self, url):
else: else:
entry['title'] = info['title'] entry['title'] = info['title']
entry['formats'].extend(info['formats']) entry['formats'].extend(info['formats'])
except Exception as e: except ExtractorError as e:
# Some playlist URL may fail with 500, at the same time # Some playlist URL may fail with 500, at the same time
# the other one may work fine (e.g. # the other one may work fine (e.g.
# http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu) # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
@ -980,6 +994,37 @@ def _real_extract(self, url):
'subtitles': subtitles, 'subtitles': subtitles,
} }
# bbc reel (e.g. https://www.bbc.com/reel/video/p07c6sb6/how-positive-thinking-is-harming-your-happiness)
initial_data = self._parse_json(self._html_search_regex(
r'<script[^>]+id=(["\'])initial-data\1[^>]+data-json=(["\'])(?P<json>(?:(?!\2).)+)',
webpage, 'initial data', default='{}', group='json'), playlist_id, fatal=False)
if initial_data:
init_data = try_get(
initial_data, lambda x: x['initData']['items'][0], dict) or {}
smp_data = init_data.get('smpData') or {}
clip_data = try_get(smp_data, lambda x: x['items'][0], dict) or {}
version_id = clip_data.get('versionID')
if version_id:
title = smp_data['title']
formats, subtitles = self._download_media_selector(version_id)
self._sort_formats(formats)
image_url = smp_data.get('holdingImageURL')
display_date = init_data.get('displayDate')
topic_title = init_data.get('topicTitle')
return {
'id': version_id,
'title': title,
'formats': formats,
'alt_title': init_data.get('shortTitle'),
'thumbnail': image_url.replace('$recipe', 'raw') if image_url else None,
'description': smp_data.get('summary') or init_data.get('shortSummary'),
'upload_date': display_date.replace('-', '') if display_date else None,
'subtitles': subtitles,
'duration': int_or_none(clip_data.get('duration')),
'categories': [topic_title] if topic_title else None,
}
# Morph based embed (e.g. http://www.bbc.co.uk/sport/live/olympics/36895975) # Morph based embed (e.g. http://www.bbc.co.uk/sport/live/olympics/36895975)
# There are several setPayload calls may be present but the video # There are several setPayload calls may be present but the video
# seems to be always related to the first one # seems to be always related to the first one
@ -1041,7 +1086,7 @@ def _real_extract(self, url):
thumbnail = None thumbnail = None
image_url = current_programme.get('image_url') image_url = current_programme.get('image_url')
if image_url: if image_url:
thumbnail = image_url.replace('{recipe}', '1920x1920') thumbnail = image_url.replace('{recipe}', 'raw')
return { return {
'id': programme_id, 'id': programme_id,
'title': title, 'title': title,

View File

@ -23,11 +23,9 @@ def _real_extract(self, url):
destination_code, content_id = re.match(self._VALID_URL, url).groups() destination_code, content_id = re.match(self._VALID_URL, url).groups()
api_base_url = self._API_BASE_TEMPLATE % (destination_code, content_id) api_base_url = self._API_BASE_TEMPLATE % (destination_code, content_id)
content = self._download_json(api_base_url, content_id, query={ content = self._download_json(api_base_url, content_id, query={
'$include': '[Media,Season,ContentPackages]', '$include': '[Media.Name,Season,ContentPackages.Duration,ContentPackages.Id]',
}) })
title = content['Name'] title = content['Name']
if len(content['ContentPackages']) > 1:
raise ExtractorError('multiple content packages')
content_package = content['ContentPackages'][0] content_package = content['ContentPackages'][0]
package_id = content_package['Id'] package_id = content_package['Id']
content_package_url = api_base_url + 'contentpackages/%s/' % package_id content_package_url = api_base_url + 'contentpackages/%s/' % package_id

View File

@ -15,17 +15,17 @@ class RDSIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?rds\.ca/vid(?:[eé]|%C3%A9)os/(?:[^/]+/)*(?P<id>[^/]+)-\d+\.\d+' _VALID_URL = r'https?://(?:www\.)?rds\.ca/vid(?:[eé]|%C3%A9)os/(?:[^/]+/)*(?P<id>[^/]+)-\d+\.\d+'
_TESTS = [{ _TESTS = [{
'url': 'http://www.rds.ca/videos/football/nfl/fowler-jr-prend-la-direction-de-jacksonville-3.1132799', # has two 9c9media ContentPackages, the web player selects the first ContentPackage
'url': 'https://www.rds.ca/videos/Hockey/NationalHockeyLeague/teams/9/forum-du-5-a-7-jesperi-kotkaniemi-de-retour-de-finlande-3.1377606',
'info_dict': { 'info_dict': {
'id': '604333', 'id': '2083309',
'display_id': 'fowler-jr-prend-la-direction-de-jacksonville', 'display_id': 'forum-du-5-a-7-jesperi-kotkaniemi-de-retour-de-finlande',
'ext': 'flv', 'ext': 'flv',
'title': 'Fowler Jr. prend la direction de Jacksonville', 'title': 'Forum du 5 à 7 : Kotkaniemi de retour de Finlande',
'description': 'Dante Fowler Jr. est le troisième choix du repêchage 2015 de la NFL. ', 'description': 'md5:83fa38ecc4a79b19e433433254077f25',
'timestamp': 1430397346, 'timestamp': 1606129030,
'upload_date': '20150430', 'upload_date': '20201123',
'duration': 154.354, 'duration': 773.039,
'age_limit': 0,
} }
}, { }, {
'url': 'http://www.rds.ca/vid%C3%A9os/un-voyage-positif-3.877934', 'url': 'http://www.rds.ca/vid%C3%A9os/un-voyage-positif-3.877934',