Compare commits

...

4 Commits

Author SHA1 Message Date
Remita Amine
3bb7769c40 [wat] remove unused variable 2021-01-21 17:22:30 +01:00
Remita Amine
8d286bd5b6 [wat] fix format extraction(closes #27901) 2021-01-21 17:20:32 +01:00
Remita Amine
cff72b4cc0 [americastestkitchen] improve season extraction 2021-01-21 16:47:55 +01:00
Brian Marks
657221c81d
[americastestkitchen] Add support for downloading entire seasons (#27861) 2021-01-21 15:46:29 +00:00
3 changed files with 84 additions and 52 deletions

View File

@ -1,6 +1,7 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import json
import re import re
from .common import InfoExtractor from .common import InfoExtractor
@ -90,3 +91,69 @@ class AmericasTestKitchenIE(InfoExtractor):
'series': try_get(episode, lambda x: x['show']['title']), 'series': try_get(episode, lambda x: x['show']['title']),
'episode': episode.get('title'), 'episode': episode.get('title'),
} }
class AmericasTestKitchenSeasonIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?P<show>americastestkitchen|cookscountry)\.com/episodes/browse/season_(?P<id>\d+)'
_TESTS = [{
# ATK Season
'url': 'https://www.americastestkitchen.com/episodes/browse/season_1',
'info_dict': {
'id': 'season_1',
'title': 'Season 1',
},
'playlist_count': 13,
}, {
# Cooks Country Season
'url': 'https://www.cookscountry.com/episodes/browse/season_12',
'info_dict': {
'id': 'season_12',
'title': 'Season 12',
},
'playlist_count': 13,
}]
def _real_extract(self, url):
show_name, season_number = re.match(self._VALID_URL, url).groups()
season_number = int(season_number)
slug = 'atk' if show_name == 'americastestkitchen' else 'cco'
season = 'Season %d' % season_number
season_search = self._download_json(
'https://y1fnzxui30-dsn.algolia.net/1/indexes/everest_search_%s_season_desc_production' % slug,
season, headers={
'Origin': 'https://www.%s.com' % show_name,
'X-Algolia-API-Key': '8d504d0099ed27c1b73708d22871d805',
'X-Algolia-Application-Id': 'Y1FNZXUI30',
}, query={
'facetFilters': json.dumps([
'search_season_list:' + season,
'search_document_klass:episode',
'search_show_slug:' + slug,
]),
'attributesToRetrieve': 'description,search_%s_episode_number,search_document_date,search_url,title' % slug,
'attributesToHighlight': '',
'hitsPerPage': 1000,
})
def entries():
for episode in (season_search.get('hits') or []):
search_url = episode.get('search_url')
if not search_url:
continue
yield {
'_type': 'url',
'url': 'https://www.%s.com%s' % (show_name, search_url),
'id': try_get(episode, lambda e: e['objectID'].split('_')[-1]),
'title': episode.get('title'),
'description': episode.get('description'),
'timestamp': unified_timestamp(episode.get('search_document_date')),
'season_number': season_number,
'episode_number': int_or_none(episode.get('search_%s_episode_number' % slug)),
'ie_key': AmericasTestKitchenIE.ie_key(),
}
return self.playlist_result(
entries(), 'season_%d' % season_number, season)

View File

@ -42,7 +42,10 @@ from .aljazeera import AlJazeeraIE
from .alphaporno import AlphaPornoIE from .alphaporno import AlphaPornoIE
from .amara import AmaraIE from .amara import AmaraIE
from .amcnetworks import AMCNetworksIE from .amcnetworks import AMCNetworksIE
from .americastestkitchen import AmericasTestKitchenIE from .americastestkitchen import (
AmericasTestKitchenIE,
AmericasTestKitchenSeasonIE,
)
from .animeondemand import AnimeOnDemandIE from .animeondemand import AnimeOnDemandIE
from .anvato import AnvatoIE from .anvato import AnvatoIE
from .aol import AolIE from .aol import AolIE

View File

@ -1,12 +1,9 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_str from ..compat import compat_str
from ..utils import ( from ..utils import (
ExtractorError,
unified_strdate, unified_strdate,
HEADRequest, HEADRequest,
int_or_none, int_or_none,
@ -46,15 +43,6 @@ class WatIE(InfoExtractor):
}, },
] ]
_FORMATS = (
(200, 416, 234),
(400, 480, 270),
(600, 640, 360),
(1200, 640, 360),
(1800, 960, 540),
(2500, 1280, 720),
)
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
video_id = video_id if video_id.isdigit() and len(video_id) > 6 else compat_str(int(video_id, 36)) video_id = video_id if video_id.isdigit() and len(video_id) > 6 else compat_str(int(video_id, 36))
@ -97,46 +85,20 @@ class WatIE(InfoExtractor):
return red_url return red_url
return None return None
def remove_bitrate_limit(manifest_url):
return re.sub(r'(?:max|min)_bitrate=\d+&?', '', manifest_url)
formats = [] formats = []
try:
alt_urls = lambda manifest_url: [re.sub(r'(?:wdv|ssm)?\.ism/', repl + '.ism/', manifest_url) for repl in ('', 'ssm')]
manifest_urls = self._download_json( manifest_urls = self._download_json(
'http://www.wat.tv/get/webhtml/' + video_id, video_id) 'http://www.wat.tv/get/webhtml/' + video_id, video_id)
m3u8_url = manifest_urls.get('hls') m3u8_url = manifest_urls.get('hls')
if m3u8_url: if m3u8_url:
m3u8_url = remove_bitrate_limit(m3u8_url)
for m3u8_alt_url in alt_urls(m3u8_url):
formats.extend(self._extract_m3u8_formats( formats.extend(self._extract_m3u8_formats(
m3u8_alt_url, video_id, 'mp4', m3u8_url, video_id, 'mp4',
'm3u8_native', m3u8_id='hls', fatal=False)) 'm3u8_native', m3u8_id='hls', fatal=False))
formats.extend(self._extract_f4m_formats(
m3u8_alt_url.replace('ios', 'web').replace('.m3u8', '.f4m'),
video_id, f4m_id='hds', fatal=False))
mpd_url = manifest_urls.get('mpd') mpd_url = manifest_urls.get('mpd')
if mpd_url: if mpd_url:
mpd_url = remove_bitrate_limit(mpd_url)
for mpd_alt_url in alt_urls(mpd_url):
formats.extend(self._extract_mpd_formats( formats.extend(self._extract_mpd_formats(
mpd_alt_url, video_id, mpd_id='dash', fatal=False)) mpd_url.replace('://das-q1.tf1.fr/', '://das-q1-ssl.tf1.fr/'),
video_id, mpd_id='dash', fatal=False))
self._sort_formats(formats) self._sort_formats(formats)
except ExtractorError:
abr = 64
for vbr, width, height in self._FORMATS:
tbr = vbr + abr
format_id = 'http-%s' % tbr
fmt_url = 'http://dnl.adv.tf1.fr/2/USP-0x0/%s/%s/%s/ssm/%s-%s-64k.mp4' % (video_id[-4:-2], video_id[-2:], video_id, video_id, vbr)
if self._is_valid_url(fmt_url, video_id, format_id):
formats.append({
'format_id': format_id,
'url': fmt_url,
'vbr': vbr,
'abr': abr,
'width': width,
'height': height,
})
date_diffusion = first_chapter.get('date_diffusion') or video_data.get('configv4', {}).get('estatS4') date_diffusion = first_chapter.get('date_diffusion') or video_data.get('configv4', {}).get('estatS4')
upload_date = unified_strdate(date_diffusion) if date_diffusion else None upload_date = unified_strdate(date_diffusion) if date_diffusion else None