youtube-dl/youtube_dl/extractor/dramafever.py

258 lines
9.0 KiB
Python
Raw Normal View History

2016-10-02 20:39:18 +09:00
# coding: utf-8
from __future__ import unicode_literals
2015-06-14 10:43:14 +09:00
import itertools
from .common import InfoExtractor
2015-06-14 10:43:14 +09:00
from ..compat import (
compat_str,
2015-06-14 10:43:14 +09:00
compat_urlparse,
)
from ..utils import (
clean_html,
ExtractorError,
2016-01-05 04:17:33 +09:00
int_or_none,
parse_age_limit,
parse_duration,
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-22 01:18:17 +09:00
sanitized_Request,
unified_timestamp,
urlencode_postdata
2015-06-14 10:43:14 +09:00
)
class DramaFeverBaseIE(InfoExtractor):
_LOGIN_URL = 'https://www.dramafever.com/accounts/login/'
_NETRC_MACHINE = 'dramafever'
_CONSUMER_SECRET = 'DA59dtVXYLxajktV'
_consumer_secret = None
def _get_consumer_secret(self):
mainjs = self._download_webpage(
'http://www.dramafever.com/static/51afe95/df2014/scripts/main.js',
None, 'Downloading main.js', fatal=False)
if not mainjs:
return self._CONSUMER_SECRET
return self._search_regex(
r"var\s+cs\s*=\s*'([^']+)'", mainjs,
'consumer secret', default=self._CONSUMER_SECRET)
def _real_initialize(self):
self._login()
self._consumer_secret = self._get_consumer_secret()
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
login_form = {
'username': username,
'password': password,
}
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-22 01:18:17 +09:00
request = sanitized_Request(
self._LOGIN_URL, urlencode_postdata(login_form))
response = self._download_webpage(
request, None, 'Logging in')
if all(logout_pattern not in response
for logout_pattern in ['href="/accounts/logout/"', '>Log out<']):
error = self._html_search_regex(
r'(?s)<h\d[^>]+\bclass="hidden-xs prompt"[^>]*>(.+?)</h\d',
response, 'error message', default=None)
if error:
raise ExtractorError('Unable to login: %s' % error, expected=True)
raise ExtractorError('Unable to log in')
class DramaFeverIE(DramaFeverBaseIE):
IE_NAME = 'dramafever'
_VALID_URL = r'https?://(?:www\.)?dramafever\.com/(?:[^/]+/)?drama/(?P<id>[0-9]+/[0-9]+)(?:/|$)'
_TESTS = [{
'url': 'https://www.dramafever.com/drama/4274/1/Heirs/',
'info_dict': {
'id': '4274.1',
'ext': 'wvm',
'title': 'Heirs - Episode 1',
'description': 'md5:362a24ba18209f6276e032a651c50bc2',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 3783,
'timestamp': 1381354993,
'upload_date': '20131009',
'series': 'Heirs',
'season_number': 1,
'episode': 'Episode 1',
'episode_number': 1,
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://www.dramafever.com/drama/4826/4/Mnet_Asian_Music_Awards_2015/?ap=1',
'info_dict': {
'id': '4826.4',
2017-07-22 13:41:40 +09:00
'ext': 'flv',
'title': 'Mnet Asian Music Awards 2015',
'description': 'md5:3ff2ee8fedaef86e076791c909cf2e91',
'episode': 'Mnet Asian Music Awards 2015 - Part 3',
'episode_number': 4,
'thumbnail': r're:^https?://.*\.jpg',
'timestamp': 1450213200,
'upload_date': '20151215',
2017-07-22 13:41:40 +09:00
'duration': 5359,
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'https://www.dramafever.com/zh-cn/drama/4972/15/Doctor_Romantic/',
'only_matching': True,
}]
def _call_api(self, path, video_id, note, fatal=False):
return self._download_json(
'https://www.dramafever.com/api/5/' + path,
video_id, note=note, headers={
'x-consumer-key': self._consumer_secret,
}, fatal=fatal)
def _get_subtitles(self, video_id):
subtitles = {}
subs = self._call_api(
'video/%s/subtitles/webvtt/' % video_id, video_id,
'Downloading subtitles JSON', fatal=False)
if not subs or not isinstance(subs, list):
return subtitles
for sub in subs:
if not isinstance(sub, dict):
continue
sub_url = sub.get('url')
if not sub_url or not isinstance(sub_url, compat_str):
continue
subtitles.setdefault(
sub.get('code') or sub.get('language') or 'en', []).append({
'url': sub_url
})
return subtitles
def _real_extract(self, url):
2015-06-14 10:43:14 +09:00
video_id = self._match_id(url).replace('/', '.')
series_id, episode_number = video_id.split('.')
video = self._call_api(
'series/%s/episodes/%s/' % (series_id, episode_number), video_id,
'Downloading video JSON')
formats = []
download_assets = video.get('download_assets')
if download_assets and isinstance(download_assets, dict):
for format_id, format_dict in download_assets.items():
if not isinstance(format_dict, dict):
continue
format_url = format_dict.get('url')
if not format_url or not isinstance(format_url, compat_str):
continue
formats.append({
'url': format_url,
'format_id': format_id,
'filesize': int_or_none(video.get('filesize')),
})
stream = self._call_api(
'video/%s/stream/' % video_id, video_id, 'Downloading stream JSON',
fatal=False)
if stream:
stream_url = stream.get('stream_url')
if stream_url:
formats.extend(self._extract_m3u8_formats(
stream_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
self._sort_formats(formats)
title = video.get('title') or 'Episode %s' % episode_number
description = video.get('description')
thumbnail = video.get('thumbnail')
timestamp = unified_timestamp(video.get('release_date'))
duration = parse_duration(video.get('duration'))
age_limit = parse_age_limit(video.get('tv_rating'))
series = video.get('series_title')
season_number = int_or_none(video.get('season'))
if series:
title = '%s - %s' % (series, title)
subtitles = self.extract_subtitles(video_id)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'timestamp': timestamp,
'age_limit': age_limit,
'series': series,
'season_number': season_number,
'episode_number': int_or_none(episode_number),
'formats': formats,
'subtitles': subtitles,
}
2015-06-14 10:43:14 +09:00
class DramaFeverSeriesIE(DramaFeverBaseIE):
IE_NAME = 'dramafever:series'
_VALID_URL = r'https?://(?:www\.)?dramafever\.com/(?:[^/]+/)?drama/(?P<id>[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$'
_TESTS = [{
'url': 'http://www.dramafever.com/drama/4512/Cooking_with_Shin/',
'info_dict': {
'id': '4512',
'title': 'Cooking with Shin',
2015-06-14 10:43:14 +09:00
'description': 'md5:84a3f26e3cdc3fb7f500211b3593b5c1',
},
'playlist_count': 4,
}, {
'url': 'http://www.dramafever.com/drama/124/IRIS/',
'info_dict': {
'id': '124',
'title': 'IRIS',
2015-06-14 10:43:14 +09:00
'description': 'md5:b3a30e587cf20c59bd1c01ec0ee1b862',
},
'playlist_count': 20,
}]
_PAGE_SIZE = 60 # max is 60 (see http://api.drama9.com/#get--api-4-episode-series-)
2015-06-14 10:43:14 +09:00
def _real_extract(self, url):
series_id = self._match_id(url)
2015-06-14 10:43:14 +09:00
series = self._download_json(
'http://www.dramafever.com/api/4/series/query/?cs=%s&series_id=%s'
% (self._consumer_secret, series_id),
2015-06-14 10:43:14 +09:00
series_id, 'Downloading series JSON')['series'][series_id]
2015-06-14 10:43:14 +09:00
title = clean_html(series['name'])
description = clean_html(series.get('description') or series.get('description_short'))
entries = []
2015-06-14 10:43:14 +09:00
for page_num in itertools.count(1):
episodes = self._download_json(
'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_size=%d&page_number=%d'
% (self._consumer_secret, series_id, self._PAGE_SIZE, page_num),
2015-06-14 10:43:14 +09:00
series_id, 'Downloading episodes JSON page #%d' % page_num)
for episode in episodes.get('value', []):
episode_url = episode.get('episode_url')
if not episode_url:
continue
2015-06-14 10:43:14 +09:00
entries.append(self.url_result(
compat_urlparse.urljoin(url, episode_url),
2015-06-14 10:43:14 +09:00
'DramaFever', episode.get('guid')))
if page_num == episodes['num_pages']:
break
return self.playlist_result(entries, series_id, title, description)