Merge remote-tracking branch 'origin/master'

2014-12-30 19:41:04 +01:00
parent 416c7fcbce e83eebb12f
commit b3013681ff
9 changed files with 469 additions and 8 deletions
--- a/youtube_dl/extractor/init.py
+++ b/youtube_dl/extractor/init.py
@@ -25,6 +25,7 @@ from .arte import (
    ArteTVDDCIE,
    ArteTVEmbedIE,
 )
+from .atresplayer import AtresPlayerIE
 from .audiomack import AudiomackIE
 from .auengine import AUEngineIE
 from .azubu import AzubuIE
@@ -169,8 +170,10 @@ from .grooveshark import GroovesharkIE
 from .groupon import GrouponIE
 from .hark import HarkIE
 from .heise import HeiseIE
+from .hellporno import HellPornoIE
 from .helsinki import HelsinkiIE
 from .hentaistigma import HentaiStigmaIE
+from .hitbox import HitboxIE, HitboxLiveIE
 from .hornbunny import HornBunnyIE
 from .hostingbulk import HostingBulkIE
 from .hotnewhiphop import HotNewHipHopIE
@@ -515,6 +518,7 @@ from .xminus import XMinusIE
 from .xnxx import XNXXIE
 from .xvideos import XVideosIE
 from .xtube import XTubeUserIE, XTubeIE
+from .xxxymovies import XXXYMoviesIE
 from .yahoo import (
    YahooIE,
    YahooSearchIE,
--- a/youtube_dl/extractor/atresplayer.py
+++ b/youtube_dl/extractor/atresplayer.py
@@ -0,0 +1,114 @@
+from __future__ import unicode_literals
+
+import time
+import hmac
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_str,
+    compat_urllib_request,
+    int_or_none,
+    float_or_none,
+    xpath_text,
+    ExtractorError,
+)
+
+
+class AtresPlayerIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?atresplayer\.com/television/[^/]+/[^/]+/[^/]+/(?P<id>.+?)_\d+\.html'
+    _TESTS = [
+        {
+            'url': 'http://www.atresplayer.com/television/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_2014122100174.html',
+            'md5': 'efd56753cda1bb64df52a3074f62e38a',
+            'info_dict': {
+                'id': 'capitulo-10-especial-solidario-nochebuena',
+                'ext': 'mp4',
+                'title': 'Especial Solidario de Nochebuena',
+                'description': 'md5:e2d52ff12214fa937107d21064075bf1',
+                'duration': 5527.6,
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+        },
+        {
+            'url': 'http://www.atresplayer.com/television/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_2014122400174.html',
+            'only_matching': True,
+        },
+    ]
+
+    _USER_AGENT = 'Dalvik/1.6.0 (Linux; U; Android 4.3; GT-I9300 Build/JSS15J'
+    _MAGIC = 'QWtMLXs414Yo+c#_+Q#K@NN)'
+    _TIMESTAMP_SHIFT = 30000
+
+    _TIME_API_URL = 'http://servicios.atresplayer.com/api/admin/time.json'
+    _URL_VIDEO_TEMPLATE = 'https://servicios.atresplayer.com/api/urlVideo/{1}/{0}/{1}|{2}|{3}.json'
+    _PLAYER_URL_TEMPLATE = 'https://servicios.atresplayer.com/episode/getplayer.json?episodePk=%s'
+    _EPISODE_URL_TEMPLATE = 'http://www.atresplayer.com/episodexml/%s'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        episode_id = self._search_regex(
+            r'episode="([^"]+)"', webpage, 'episode id')
+
+        timestamp = int_or_none(self._download_webpage(
+            self._TIME_API_URL,
+            video_id, 'Downloading timestamp', fatal=False), 1000, time.time())
+        timestamp_shifted = compat_str(timestamp + self._TIMESTAMP_SHIFT)
+        token = hmac.new(
+            self._MAGIC.encode('ascii'),
+            (episode_id + timestamp_shifted).encode('utf-8')
+        ).hexdigest()
+
+        formats = []
+        for fmt in ['windows', 'android_tablet']:
+            request = compat_urllib_request.Request(
+                self._URL_VIDEO_TEMPLATE.format(fmt, episode_id, timestamp_shifted, token))
+            request.add_header('Youtubedl-user-agent', self._USER_AGENT)
+
+            fmt_json = self._download_json(
+                request, video_id, 'Downloading %s video JSON' % fmt)
+
+            result = fmt_json.get('resultDes')
+            if result.lower() != 'ok':
+                raise ExtractorError(
+                    '%s returned error: %s' % (self.IE_NAME, result), expected=True)
+
+            for _, video_url in fmt_json['resultObject'].items():
+                if video_url.endswith('/Manifest'):
+                    formats.extend(self._extract_f4m_formats(video_url[:-9] + '/manifest.f4m', video_id))
+                else:
+                    formats.append({
+                        'url': video_url,
+                        'format_id': 'android',
+                        'preference': 1,
+                    })
+        self._sort_formats(formats)
+
+        player = self._download_json(
+            self._PLAYER_URL_TEMPLATE % episode_id,
+            episode_id)
+
+        path_data = player.get('pathData')
+
+        episode = self._download_xml(
+            self._EPISODE_URL_TEMPLATE % path_data,
+            video_id, 'Downloading episode XML')
+
+        duration = float_or_none(xpath_text(
+            episode, './media/asset/info/technical/contentDuration', 'duration'))
+
+        art = episode.find('./media/asset/info/art')
+        title = xpath_text(art, './name', 'title')
+        description = xpath_text(art, './description', 'description')
+        thumbnail = xpath_text(episode, './media/asset/files/background', 'thumbnail')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+        }
--- a/youtube_dl/extractor/cnn.py
+++ b/youtube_dl/extractor/cnn.py
@@ -12,7 +12,7 @@ from ..utils import (

 class CNNIE(InfoExtractor):
    _VALID_URL = r'''(?x)https?://(?:(?:edition|www)\.)?cnn\.com/video/(?:data/.+?|\?)/
-        (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn(?:-ap)?|(?=&)))'''
+        (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:cnn|hln)(?:-ap)?|(?=&)))'''

    _TESTS = [{
        'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
@@ -35,6 +35,16 @@ class CNNIE(InfoExtractor):
            "description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"",
            "upload_date": "20130821",
        }
+    }, {
+        'url': 'http://www.cnn.com/video/data/2.0/video/living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln.html',
+        'md5': 'f14d02ebd264df951feb2400e2c25a1b',
+        'info_dict': {
+            'id': 'living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln',
+            'ext': 'mp4',
+            'title': 'Nashville Ep. 1: Hand crafted skateboards',
+            'description': 'md5:e7223a503315c9f150acac52e76de086',
+            'upload_date': '20141222',
+        }
    }]

    def _real_extract(self, url):
--- a/youtube_dl/extractor/daum.py
+++ b/youtube_dl/extractor/daum.py
@@ -38,7 +38,7 @@ class DaumIE(InfoExtractor):
        canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
        webpage = self._download_webpage(canonical_url, video_id)
        full_id = self._search_regex(
-            r'<iframe src="http://videofarm.daum.net/controller/video/viewer/Video.html\?.*?vid=(.+?)[&"]',
+            r'src=["\']http://videofarm\.daum\.net/controller/video/viewer/Video\.html\?.*?vid=(.+?)[&"\']',
            webpage, 'full id')
        query = compat_urllib_parse.urlencode({'vid': full_id})
        info = self._download_xml(
--- a/youtube_dl/extractor/hellporno.py
+++ b/youtube_dl/extractor/hellporno.py
@@ -0,0 +1,71 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    js_to_json,
+    remove_end,
+)
+
+
+class HellPornoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?hellporno\.com/videos/(?P<id>[^/]+)'
+    _TEST = {
+        'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/',
+        'md5': '1fee339c610d2049699ef2aa699439f1',
+        'info_dict': {
+            'id': '149116',
+            'display_id': 'dixie-is-posing-with-naked-ass-very-erotic',
+            'ext': 'mp4',
+            'title': 'Dixie is posing with naked ass very erotic',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        title = remove_end(self._html_search_regex(
+            r'<title>([^<]+)</title>', webpage, 'title'), ' - Hell Porno')
+
+        flashvars = self._parse_json(self._search_regex(
+            r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'),
+            display_id, transform_source=js_to_json)
+
+        video_id = flashvars.get('video_id')
+        thumbnail = flashvars.get('preview_url')
+        ext = flashvars.get('postfix', '.mp4')[1:]
+
+        formats = []
+        for video_url_key in ['video_url', 'video_alt_url']:
+            video_url = flashvars.get(video_url_key)
+            if not video_url:
+                continue
+            video_text = flashvars.get('%s_text' % video_url_key)
+            fmt = {
+                'url': video_url,
+                'ext': ext,
+                'format_id': video_text,
+            }
+            m = re.search(r'^(?P<height>\d+)[pP]', video_text)
+            if m:
+                fmt['height'] = int(m.group('height'))
+            formats.append(fmt)
+        self._sort_formats(formats)
+
+        categories = self._html_search_meta(
+            'keywords', webpage, 'categories', default='').split(',')
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'categories': categories,
+            'age_limit': 18,
+            'formats': formats,
+        }
--- a/youtube_dl/extractor/hitbox.py
+++ b/youtube_dl/extractor/hitbox.py
@@ -0,0 +1,166 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    parse_iso8601,
+    float_or_none,
+    int_or_none,
+    compat_str,
+)
+
+
+class HitboxIE(InfoExtractor):
+    IE_NAME = 'hitbox'
+    _VALID_URL = r'https?://(?:www\.)?hitbox\.tv/video/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.hitbox.tv/video/203213',
+        'info_dict': {
+            'id': '203213',
+            'title': 'hitbox @ gamescom, Sub Button Hype extended, Giveaway - hitbox News Update with Oxy',
+            'alt_title': 'hitboxlive - Aug 9th #6',
+            'description': '',
+            'ext': 'mp4',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 215.1666,
+            'resolution': 'HD 720p',
+            'uploader': 'hitboxlive',
+            'view_count': int,
+            'timestamp': 1407576133,
+            'upload_date': '20140809',
+            'categories': ['Live Show'],
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _extract_metadata(self, url, video_id):
+        thumb_base = 'https://edge.sf.hitbox.tv'
+        metadata = self._download_json(
+            '%s/%s' % (url, video_id), video_id)
+
+        date = 'media_live_since'
+        media_type = 'livestream'
+        if metadata.get('media_type') == 'video':
+            media_type = 'video'
+            date = 'media_date_added'
+
+        video_meta = metadata.get(media_type, [])[0]
+        title = video_meta.get('media_status')
+        alt_title = video_meta.get('media_title')
+        description = clean_html(
+            video_meta.get('media_description') or
+            video_meta.get('media_description_md'))
+        duration = float_or_none(video_meta.get('media_duration'))
+        uploader = video_meta.get('media_user_name')
+        views = int_or_none(video_meta.get('media_views'))
+        timestamp = parse_iso8601(video_meta.get(date), ' ')
+        categories = [video_meta.get('category_name')]
+        thumbs = [
+            {'url': thumb_base + video_meta.get('media_thumbnail'),
+             'width': 320,
+             'height': 180},
+            {'url': thumb_base + video_meta.get('media_thumbnail_large'),
+             'width': 768,
+             'height': 432},
+        ]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'alt_title': alt_title,
+            'description': description,
+            'ext': 'mp4',
+            'thumbnails': thumbs,
+            'duration': duration,
+            'uploader': uploader,
+            'view_count': views,
+            'timestamp': timestamp,
+            'categories': categories,
+        }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        metadata = self._extract_metadata(
+            'https://www.hitbox.tv/api/media/video',
+            video_id)
+
+        player_config = self._download_json(
+            'https://www.hitbox.tv/api/player/config/video/%s' % video_id,
+            video_id)
+
+        clip = player_config.get('clip')
+        video_url = clip.get('url')
+        res = clip.get('bitrates', [])[0].get('label')
+
+        metadata['resolution'] = res
+        metadata['url'] = video_url
+        metadata['protocol'] = 'm3u8'
+
+        return metadata
+
+
+class HitboxLiveIE(HitboxIE):
+    IE_NAME = 'hitbox:live'
+    _VALID_URL = r'https?://(?:www\.)?hitbox\.tv/(?!video)(?P<id>.+)'
+    _TEST = {
+        'url': 'http://www.hitbox.tv/dimak',
+        'info_dict': {
+            'id': 'dimak',
+            'ext': 'mp4',
+            'description': 'md5:c9f80fa4410bc588d7faa40003fc7d0e',
+            'timestamp': int,
+            'upload_date': compat_str,
+            'title': compat_str,
+            'uploader': 'Dimak',
+        },
+        'params': {
+            # live
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        metadata = self._extract_metadata(
+            'https://www.hitbox.tv/api/media/live',
+            video_id)
+
+        player_config = self._download_json(
+            'https://www.hitbox.tv/api/player/config/live/%s' % video_id,
+            video_id)
+
+        formats = []
+        cdns = player_config.get('cdns')
+        servers = []
+        for cdn in cdns:
+            base_url = cdn.get('netConnectionUrl')
+            host = re.search('.+\.([^\.]+\.[^\./]+)/.+', base_url).group(1)
+            if base_url not in servers:
+                servers.append(base_url)
+                for stream in cdn.get('bitrates'):
+                    label = stream.get('label')
+                    if label != 'Auto':
+                        formats.append({
+                            'url': '%s/%s' % (base_url, stream.get('url')),
+                            'ext': 'mp4',
+                            'vbr': stream.get('bitrate'),
+                            'resolution': label,
+                            'rtmp_live': True,
+                            'format_note': host,
+                            'page_url': url,
+                            'player_url': 'http://www.hitbox.tv/static/player/flowplayer/flowplayer.commercial-3.2.16.swf',
+                        })
+
+        self._sort_formats(formats)
+        metadata['formats'] = formats
+        metadata['is_live'] = True
+        metadata['title'] = self._live_title(metadata.get('title'))
+        return metadata
--- a/youtube_dl/extractor/xxxymovies.py
+++ b/youtube_dl/extractor/xxxymovies.py
@@ -0,0 +1,81 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    int_or_none,
+)
+
+
+class XXXYMoviesIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?xxxymovies\.com/videos/(?P<id>\d+)/(?P<display_id>[^/]+)'
+    _TEST = {
+        'url': 'http://xxxymovies.com/videos/138669/ecstatic-orgasm-sofcore/',
+        'md5': '810b1bdbbffff89dd13bdb369fe7be4b',
+        'info_dict': {
+            'id': '138669',
+            'display_id': 'ecstatic-orgasm-sofcore',
+            'ext': 'mp4',
+            'title': 'Ecstatic Orgasm Sofcore',
+            'duration': 931,
+            'categories': list,
+            'view_count': int,
+            'like_count': int,
+            'dislike_count': int,
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_url = self._search_regex(
+            r"video_url\s*:\s*'([^']+)'", webpage, 'video URL')
+
+        title = self._html_search_regex(
+            [r'<div class="block_header">\s*<h1>([^<]+)</h1>',
+             r'<title>(.*?)\s*-\s*XXXYMovies\.com</title>'],
+            webpage, 'title')
+
+        thumbnail = self._search_regex(
+            r"preview_url\s*:\s*'([^']+)'",
+            webpage, 'thumbnail', fatal=False)
+
+        categories = self._html_search_meta(
+            'keywords', webpage, 'categories', default='').split(',')
+
+        duration = parse_duration(self._search_regex(
+            r'<span>Duration:</span>\s*(\d+:\d+)',
+            webpage, 'duration', fatal=False))
+
+        view_count = int_or_none(self._html_search_regex(
+            r'<div class="video_views">\s*(\d+)',
+            webpage, 'view count', fatal=False))
+        like_count = int_or_none(self._search_regex(
+            r'>\s*Likes? <b>\((\d+)\)',
+            webpage, 'like count', fatal=False))
+        dislike_count = int_or_none(self._search_regex(
+            r'>\s*Dislike <b>\((\d+)\)</b>',
+            webpage, 'dislike count', fatal=False))
+
+        age_limit = self._rta_search(webpage)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': video_url,
+            'title': title,
+            'thumbnail': thumbnail,
+            'categories': categories,
+            'duration': duration,
+            'view_count': view_count,
+            'like_count': like_count,
+            'dislike_count': dislike_count,
+            'age_limit': age_limit,
+        }
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -418,6 +418,19 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                'upload_date': '20140605',
            },
        },
+        # Age-gate video with encrypted signature
+        {
+            'url': 'http://www.youtube.com/watch?v=6kLq3WMV1nU',
+            'info_dict': {
+                'id': '6kLq3WMV1nU',
+                'ext': 'mp4',
+                'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
+                'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
+                'uploader': 'LloydVEVO',
+                'uploader_id': 'LloydVEVO',
+                'upload_date': '20110629',
+            },
+        },
        # video_info is None (https://github.com/rg3/youtube-dl/issues/4421)
        {
            'url': '__2ABJjxzNo',
@@ -766,11 +779,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
            age_gate = True
            # We simulate the access to the video from www.youtube.com/v/{video_id}
            # this can be viewed without login into Youtube
+            url = proto + '://www.youtube.com/embed/%s' % video_id
+            embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
            data = compat_urllib_parse.urlencode({
                'video_id': video_id,
                'eurl': 'https://youtube.googleapis.com/v/' + video_id,
                'sts': self._search_regex(
-                    r'"sts"\s*:\s*(\d+)', video_webpage, 'sts', default=''),
+                    r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
            })
            video_info_url = proto + '://www.youtube.com/get_video_info?' + data
            video_info_webpage = self._download_webpage(
@@ -968,11 +983,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                elif 's' in url_data:
                    encrypted_sig = url_data['s'][0]

-                    if not age_gate:
-                        jsplayer_url_json = self._search_regex(
-                            r'"assets":.+?"js":\s*("[^"]+")',
-                            video_webpage, 'JS player URL')
-                        player_url = json.loads(jsplayer_url_json)
+                    jsplayer_url_json = self._search_regex(
+                        r'"assets":.+?"js":\s*("[^"]+")',
+                        embed_webpage if age_gate else video_webpage, 'JS player URL')
+                    player_url = json.loads(jsplayer_url_json)
                    if player_url is None:
                        player_url_json = self._search_regex(
                            r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',