R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[puhutv] improvement

Browse Source
This commit is contained in:
Enes 2018-06-05 20:19:05 +03:00
parent f5f1ca8880
commit b521306bb5
1 changed files with 49 additions and 66 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

115
youtube_dl/extractor/puhutv.py
View File

@ -10,14 +10,18 @@ from ..utils import (
parse_iso8601, parse_iso8601,
str_or_none, str_or_none,
unified_strdate, unified_strdate,
urljoin urljoin,
url_basename,
remove_end
) )
class PuhuTVIE(InfoExtractor): class PuhuTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?puhutv\.com/(?P<id>[a-z0-9-]+)-izle' _VALID_URL = r'https?://(?:www\.)?puhutv\.com/(?P<id>[a-z0-9-]+)-izle'
IE_NAME = 'puhutv'
_TESTS = [ _TESTS = [
{ # A Film {
# A Film
'url': 'https://puhutv.com/sut-kardesler-izle', 'url': 'https://puhutv.com/sut-kardesler-izle',
'md5': 'a347470371d56e1585d1b2c8dab01c96', 'md5': 'a347470371d56e1585d1b2c8dab01c96',
'info_dict': { 'info_dict': {
@ -33,44 +37,18 @@ class PuhuTVIE(InfoExtractor):
'timestamp': int, 'timestamp': int,
}, },
}, },
{ # An Episode and geo restricted {
# An Episode and geo restricted
'url': 'https://puhutv.com/jet-sosyete-1-bolum-izle', 'url': 'https://puhutv.com/jet-sosyete-1-bolum-izle',
'md5': '3cd1f4b931cff5e009dfa46a3b88a42a', 'only_matching': True,
'info_dict': {
'id': 'jet-sosyete-1-bolum',
'display_id': '18501',
'ext': 'mp4',
'title': 'Jet Sosyete 1. Sezon 1. Bölüm',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'BKM',
'description': 'md5:18ba5abe6d19f8063a8348445c41e28f',
'uploader_id': '269',
'upload_date': '20180220',
'timestamp': int,
},
}, },
{ # Has subtitle {
# Has subtitle
'url': 'https://puhutv.com/dip-1-bolum-izle', 'url': 'https://puhutv.com/dip-1-bolum-izle',
'md5': 'f27792b1169f42ab318c38887ad5b28e', 'only_matching': True,
'info_dict': {
'id': 'dip-1-bolum',
'display_id': '18944',
'ext': 'mp4',
'title': 'Dip 1. Sezon 1. Bölüm',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'TMC',
'description': 'md5:e8ddb56738b093b4eae0a536e2ea02c2',
'uploader_id': '25',
'upload_date': '20180330',
'timestamp': int,
},
'params': {
'skip_download': True,
}
} }
] ]
IE_NAME = 'puhutv' _SUBTITLE_LANGS = {
_SUBTITLE_LANGS = { # currently supported for some series
'English': 'en', 'English': 'en',
'Deutsch': 'de', 'Deutsch': 'de',
'عربى': 'ar' 'عربى': 'ar'
@ -78,17 +56,15 @@ class PuhuTVIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
# API call
info = self._download_json( info = self._download_json(
'https://puhutv.com/api/slug/%s-izle' % video_id, video_id) 'https://puhutv.com/api/slug/%s-izle' % video_id, video_id)['data']
info = info.get('data') display_id = compat_str(info['id'])
display_id = compat_str(info.get('id')) title = info['title']['name']
title = info.get('title').get('name')
if(info.get('display_name') and title is not None): if(info.get('display_name') and title is not None):
title += ' ' + info.get('display_name') title += ' ' + info.get('display_name')
description = info.get('title', {}).get('description')
description = info.get('title', {}).get('description') or info.get('description')
timestamp = parse_iso8601(info.get('created_at')) timestamp = parse_iso8601(info.get('created_at'))
upload_date = unified_strdate(info.get('created_at')) upload_date = unified_strdate(info.get('created_at'))
uploader = info.get('title', {}).get('producer', {}).get('name') uploader = info.get('title', {}).get('producer', {}).get('name')
@ -98,9 +74,6 @@ class PuhuTVIE(InfoExtractor):
thumbnail = urljoin('https://', info.get('content', {}).get('images', {}).get('wide', {}).get('main')) thumbnail = urljoin('https://', info.get('content', {}).get('images', {}).get('wide', {}).get('main'))
release_year = int_or_none(info.get('title', {}).get('released_at')) release_year = int_or_none(info.get('title', {}).get('released_at'))
webpage_url = info.get('web_url') webpage_url = info.get('web_url')
tags_list = info.get('title', {}).get('genres', {})
thumbnails_list = info.get('content', {}).get('images', {}).get('wide', {})
subtitles_list = info.get('content', {}).get('subtitles', {})
# for series # for series
season_number = int_or_none(info.get('season_number')) season_number = int_or_none(info.get('season_number'))
@ -108,24 +81,29 @@ class PuhuTVIE(InfoExtractor):
episode_number = int_or_none(info.get('episode_number')) episode_number = int_or_none(info.get('episode_number'))
tags = [] tags = []
for tag in tags_list: for tag in info.get('title', {}).get('genres', {}):
if tag.get('name'): if isinstance(tag.get('name'), compat_str):
tags.append(tag.get('name')) tags.append(tag.get('name'))
thumbnails = [] thumbnails = []
for id, url in thumbnails_list.items(): thumbs_dict = info.get('content', {}).get('images', {}).get('wide', {})
url = urljoin('https://', url) if isinstance(thumbs_dict, dict):
thumbnails.append({ for id, url in thumbs_dict.items():
'url': url, if not url or not isinstance(url, compat_str):
'id': id continue
}) url = urljoin('https://', url)
thumbnails.append({
'url': url,
'id': id
})
subtitles = {} subtitles = {}
for subtitle in subtitles_list: for subtitle in info.get('content', {}).get('subtitles', {}):
if not isinstance(subtitle, dict):
continue
lang = subtitle.get('language') lang = subtitle.get('language')
sub_url = subtitle.get('url') sub_url = subtitle.get('url')
# If the keys were changed by api, continue if not lang or not isinstance(lang, compat_str) or not sub_url or not isinstance(sub_url, compat_str):
if not lang or not sub_url:
continue continue
subtitles[self._SUBTITLE_LANGS.get(lang, lang)] = [{ subtitles[self._SUBTITLE_LANGS.get(lang, lang)] = [{
'url': sub_url, 'url': sub_url,
@ -138,20 +116,25 @@ class PuhuTVIE(InfoExtractor):
video_id, 'Downloading video JSON', fatal=False) video_id, 'Downloading video JSON', fatal=False)
if not req_formats: if not req_formats:
self.raise_geo_restricted() self.raise_geo_restricted()
else:
format_dict = req_formats.get('data').get('videos')
formats = [] formats = []
for format in format_dict: for format in req_formats['data']['videos']:
media_url = format.get('url') media_url = format.get('url')
if not media_url or not isinstance(media_url, compat_str):
continue
ext = format.get('video_format') or determine_ext(media_url) ext = format.get('video_format') or determine_ext(media_url)
quality = format.get('quality') quality = format.get('quality')
if ext == 'mp4' and format.get('is_playlist', False) is False: if format.get('stream_type') == 'hls' and format.get('is_playlist') is True:
m3u8_id = remove_end(url_basename(media_url), '.m3u8')
formats.append(self._m3u8_meta_format(media_url, ext, m3u8_id=m3u8_id))
elif ext == 'mp4' and format.get('is_playlist', False) is False:
formats.append({ formats.append({
'url': media_url, 'url': media_url,
'format_id': 'http-%s' % quality, 'format_id': 'http-%s' % quality,
'ext': ext 'ext': ext,
'height': quality
}) })
self._sort_formats(formats)
return { return {
'id': video_id, 'id': video_id,
@ -191,7 +174,8 @@ class PuhuTVSerieIE(InfoExtractor):
}, },
'playlist_mincount': 234, 'playlist_mincount': 234,
}, },
{ # a film detail page which is using same url with serie page {
# a film detail page which is using same url with serie page
'url': 'https://puhutv.com/kaybedenler-kulubu-detay', 'url': 'https://puhutv.com/kaybedenler-kulubu-detay',
'info_dict': { 'info_dict': {
'title': 'Kaybedenler Kulübü', 'title': 'Kaybedenler Kulübü',
@ -205,7 +189,7 @@ class PuhuTVSerieIE(InfoExtractor):
def _extract_entries(self, playlist_id, seasons): def _extract_entries(self, playlist_id, seasons):
for season in seasons: for season in seasons:
season_id = season.get('id') season_id = season['id']
season_number = season.get('position') season_number = season.get('position')
pagenum = 1 pagenum = 1
has_more = True has_more = True
@ -218,7 +202,7 @@ class PuhuTVSerieIE(InfoExtractor):
'https://galadriel.puhutv.com/seasons/%s' % season_id, 'https://galadriel.puhutv.com/seasons/%s' % season_id,
playlist_id, 'Downloading season %s page %s' % (season_number, pagenum), query=query) playlist_id, 'Downloading season %s page %s' % (season_number, pagenum), query=query)
for episode in season_info.get('episodes'): for episode in season_info.get('episodes'):
video_id = episode.get('slugPath').replace('-izle', '') video_id = episode['slugPath'].replace('-izle', '')
yield self.url_result( yield self.url_result(
'https://puhutv.com/%s-izle' % video_id, 'https://puhutv.com/%s-izle' % video_id,
PuhuTVIE.ie_key(), video_id) PuhuTVIE.ie_key(), video_id)
@ -229,8 +213,7 @@ class PuhuTVSerieIE(InfoExtractor):
playlist_id = self._match_id(url) playlist_id = self._match_id(url)
info = self._download_json( info = self._download_json(
'https://puhutv.com/api/slug/%s-detay' % playlist_id, 'https://puhutv.com/api/slug/%s-detay' % playlist_id, playlist_id)['data']
playlist_id).get('data')
title = info.get('name') title = info.get('name')
uploader = info.get('producer', {}).get('name') uploader = info.get('producer', {}).get('name')
@ -240,7 +223,7 @@ class PuhuTVSerieIE(InfoExtractor):
entries = self._extract_entries(playlist_id, seasons) entries = self._extract_entries(playlist_id, seasons)
else: else:
# For films, these are using same url with series # For films, these are using same url with series
video_id = info.get('assets')[0].get('slug') video_id = info['assets'][0]['slug']
return self.url_result( return self.url_result(
'https://puhutv.com/%s-izle' % video_id, 'https://puhutv.com/%s-izle' % video_id,
PuhuTVIE.ie_key(), video_id) PuhuTVIE.ie_key(), video_id)