0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 03:03:01 +00:00
yt-dlp/youtube_dl/extractor/puhutv.py

248 lines
8.5 KiB
Python
Raw Normal View History

2018-04-24 16:02:38 +00:00
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
compat_str,
)
2018-04-24 16:02:38 +00:00
from ..utils import (
ExtractorError,
2018-04-24 16:02:38 +00:00
int_or_none,
float_or_none,
parse_resolution,
2018-04-24 16:02:38 +00:00
str_or_none,
try_get,
unified_timestamp,
url_or_none,
urljoin,
2018-04-24 16:02:38 +00:00
)
class PuhuTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?puhutv\.com/(?P<id>[^/?#&]+)-izle'
2018-04-24 16:02:38 +00:00
IE_NAME = 'puhutv'
_TESTS = [{
# film
'url': 'https://puhutv.com/sut-kardesler-izle',
'md5': 'fbd8f2d8e7681f8bcd51b592475a6ae7',
'info_dict': {
'id': '5085',
'display_id': 'sut-kardesler',
'ext': 'mp4',
'title': 'Süt Kardeşler',
'description': 'md5:405fd024df916ca16731114eb18e511a',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 4832.44,
'creator': 'Arzu Film',
'timestamp': 1469778212,
'upload_date': '20160729',
'release_year': 1976,
'view_count': int,
'tags': ['Aile', 'Komedi', 'Klasikler'],
2018-04-24 16:02:38 +00:00
},
}, {
# episode, geo restricted, bypassable with --geo-verification-proxy
'url': 'https://puhutv.com/jet-sosyete-1-bolum-izle',
'only_matching': True,
}, {
# 4k, with subtitles
'url': 'https://puhutv.com/dip-1-bolum-izle',
'only_matching': True,
}]
2018-04-24 16:02:38 +00:00
_SUBTITLE_LANGS = {
'English': 'en',
'Deutsch': 'de',
'عربى': 'ar'
}
def _real_extract(self, url):
display_id = self._match_id(url)
2018-04-24 16:02:38 +00:00
info = self._download_json(
urljoin(url, '/api/slug/%s-izle' % display_id),
display_id)['data']
2018-04-24 16:02:38 +00:00
video_id = compat_str(info['id'])
title = info.get('name') or info['title']['name']
2018-04-24 16:02:38 +00:00
if info.get('display_name'):
title = '%s %s' % (title, info.get('display_name'))
try:
videos = self._download_json(
'https://puhutv.com/api/assets/%s/videos' % video_id,
display_id, 'Downloading video JSON',
headers=self.geo_verification_headers())
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
self.raise_geo_restricted()
raise
formats = []
for video in videos['data']['videos']:
media_url = url_or_none(video.get('url'))
if not media_url:
continue
playlist = video.get('is_playlist')
if video.get('stream_type') == 'hls' and playlist is True:
formats.extend(self._extract_m3u8_formats(
media_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
continue
quality = int_or_none(video.get('quality'))
f = {
'url': media_url,
'ext': 'mp4',
'height': quality
}
video_format = video.get('video_format')
if video_format == 'hls' and playlist is False:
format_id = 'hls'
f['protocol'] = 'm3u8_native'
elif video_format == 'mp4':
format_id = 'http'
else:
continue
if quality:
format_id += '-%sp' % quality
f['format_id'] = format_id
formats.append(f)
self._sort_formats(formats)
description = try_get(
info, lambda x: x['title']['description'],
compat_str) or info.get('description')
2018-04-24 16:02:38 +00:00
timestamp = unified_timestamp(info.get('created_at'))
creator = try_get(
info, lambda x: x['title']['producer']['name'], compat_str)
duration = float_or_none(
try_get(info, lambda x: x['content']['duration_in_ms'], int),
scale=1000)
view_count = try_get(info, lambda x: x['content']['watch_count'], int)
images = try_get(
info, lambda x: x['content']['images']['wide'], dict) or {}
thumbnails = []
for image_id, image_url in images.items():
if not isinstance(image_url, compat_str):
continue
if not image_url.startswith(('http', '//')):
image_url = 'https://%s' % image_url
t = parse_resolution(image_id)
t.update({
'id': image_id,
'url': image_url
})
thumbnails.append(t)
release_year = try_get(info, lambda x: x['title']['released_at'], int)
2018-04-24 16:02:38 +00:00
season_number = int_or_none(info.get('season_number'))
season_id = str_or_none(info.get('season_id'))
2018-04-24 16:02:38 +00:00
episode_number = int_or_none(info.get('episode_number'))
tags = []
for genre in try_get(info, lambda x: x['title']['genres'], list) or []:
if not isinstance(genre, dict):
2018-04-24 16:02:38 +00:00
continue
genre_name = genre.get('name')
if genre_name and isinstance(genre_name, compat_str):
tags.append(genre_name)
2018-04-24 16:02:38 +00:00
subtitles = {}
for subtitle in try_get(
info, lambda x: x['content']['subtitles'], list) or []:
2018-04-24 16:02:38 +00:00
if not isinstance(subtitle, dict):
continue
lang = subtitle.get('language')
sub_url = url_or_none(subtitle.get('url'))
if not lang or not isinstance(lang, compat_str) or not sub_url:
continue
subtitles[self._SUBTITLE_LANGS.get(lang, lang)] = [{
'url': sub_url
}]
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'season_id': season_id,
'season_number': season_number,
'episode_number': episode_number,
'release_year': release_year,
'timestamp': timestamp,
'creator': creator,
2018-04-24 16:02:38 +00:00
'view_count': view_count,
'duration': duration,
'tags': tags,
'subtitles': subtitles,
'thumbnails': thumbnails,
'formats': formats
}
class PuhuTVSerieIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?puhutv\.com/(?P<id>[^/?#&]+)-detay'
2018-04-24 16:02:38 +00:00
IE_NAME = 'puhutv:serie'
_TESTS = [{
'url': 'https://puhutv.com/deniz-yildizi-detay',
'info_dict': {
'title': 'Deniz Yıldızı',
'id': 'deniz-yildizi',
2018-04-24 16:02:38 +00:00
},
'playlist_mincount': 205,
}, {
# a film detail page which is using same url with serie page
'url': 'https://puhutv.com/kaybedenler-kulubu-detay',
'only_matching': True,
}]
def _extract_entries(self, seasons):
2018-04-24 16:02:38 +00:00
for season in seasons:
season_id = season.get('id')
if not season_id:
continue
page = 1
2018-04-24 16:02:38 +00:00
has_more = True
while has_more is True:
season = self._download_json(
2018-04-24 16:02:38 +00:00
'https://galadriel.puhutv.com/seasons/%s' % season_id,
season_id, 'Downloading page %s' % page, query={
'page': page,
2018-04-24 16:02:38 +00:00
'per': 40,
})
episodes = season.get('episodes')
if isinstance(episodes, list):
for ep in episodes:
slug_path = str_or_none(ep.get('slugPath'))
if not slug_path:
continue
video_id = str_or_none(int_or_none(ep.get('id')))
yield self.url_result(
'https://puhutv.com/%s' % slug_path,
ie=PuhuTVIE.ie_key(), video_id=video_id,
video_title=ep.get('name') or ep.get('eventLabel'))
page += 1
has_more = season.get('hasMore')
2018-04-24 16:02:38 +00:00
def _real_extract(self, url):
playlist_id = self._match_id(url)
info = self._download_json(
urljoin(url, '/api/slug/%s-detay' % playlist_id),
playlist_id)['data']
2018-04-24 16:02:38 +00:00
seasons = info.get('seasons')
if seasons:
return self.playlist_result(
self._extract_entries(seasons), playlist_id, info.get('name'))
# For films, these are using same url with series
video_id = info.get('slug') or info['assets'][0]['slug']
return self.url_result(
'https://puhutv.com/%s-izle' % video_id,
PuhuTVIE.ie_key(), video_id)