release 2014.09.10

[sharesix] Add new extractor

youtube_dl/extractor/__init__.py

@@ -200,6 +200,7 @@ from .mitele import MiTeleIE
 from .mixcloud import MixcloudIE
 from .mlb import MLBIE
 from .mpora import MporaIE
+from .moevideo import MoeVideoIE
 from .mofosex import MofosexIE
 from .mojvideo import MojvideoIE
 from .mooshare import MooshareIE
@@ -296,6 +297,7 @@ from .scivee import SciVeeIE
 from .screencast import ScreencastIE
 from .servingsys import ServingSysIE
 from .shared import SharedIE
+from .sharesix import ShareSixIE
 from .sina import SinaIE
 from .slideshare import SlideshareIE
 from .slutload import SlutloadIE
@@ -375,6 +377,7 @@ from .veehd import VeeHDIE
 from .veoh import VeohIE
 from .vesti import VestiIE
 from .vevo import VevoIE
+from .vgtv import VGTVIE
 from .vh1 import VH1IE
 from .viddler import ViddlerIE
 from .videobam import VideoBamIE

youtube_dl/extractor/khanacademy.py

@@ -9,7 +9,7 @@ from ..utils import (
 
 
 class KhanAcademyIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:www\.)?khanacademy\.org/(?P<key>[^/]+)/(?:[^/]+/){,2}(?P<id>[^?#/]+)(?:$|[?#])'
+    _VALID_URL = r'^https?://(?:(?:www|api)\.)?khanacademy\.org/(?P<key>[^/]+)/(?:[^/]+/){,2}(?P<id>[^?#/]+)(?:$|[?#])'
     IE_NAME = 'KhanAcademy'
 
     _TESTS = [{

youtube_dl/extractor/moevideo.py

@@ -0,0 +1,112 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    compat_urllib_parse,
+    compat_urllib_request,
+    int_or_none,
+)
+
+
+class MoeVideoIE(InfoExtractor):
+    IE_DESC = 'LetitBit video services: moevideo.net, playreplay.net and videochart.net'
+    _VALID_URL = r'''(?x)
+        https?://(?P<host>(?:www\.)?
+        (?:(?:moevideo|playreplay|videochart)\.net))/
+        (?:video|framevideo)/(?P<id>[0-9]+\.[0-9A-Za-z]+)'''
+    _API_URL = 'http://api.letitbit.net/'
+    _API_KEY = 'tVL0gjqo5'
+    _TESTS = [
+        {
+            'url': 'http://moevideo.net/video/00297.0036103fe3d513ef27915216fd29',
+            'md5': '129f5ae1f6585d0e9bb4f38e774ffb3a',
+            'info_dict': {
+                'id': '00297.0036103fe3d513ef27915216fd29',
+                'ext': 'flv',
+                'title': 'Sink cut out machine',
+                'description': 'md5:f29ff97b663aefa760bf7ca63c8ca8a8',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'width': 540,
+                'height': 360,
+                'duration': 179,
+                'filesize': 17822500,
+            }
+        },
+        {
+            'url': 'http://playreplay.net/video/77107.7f325710a627383d40540d8e991a',
+            'md5': '74f0a014d5b661f0f0e2361300d1620e',
+            'info_dict': {
+                'id': '77107.7f325710a627383d40540d8e991a',
+                'ext': 'flv',
+                'title': 'Operacion Condor.',
+                'description': 'md5:7e68cb2fcda66833d5081c542491a9a3',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'width': 480,
+                'height': 296,
+                'duration': 6027,
+                'filesize': 588257923,
+            }
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(
+            'http://%s/video/%s' % (mobj.group('host'), video_id),
+            video_id, 'Downloading webpage')
+
+        title = self._og_search_title(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+        description = self._og_search_description(webpage)
+
+        r = [
+            self._API_KEY,
+            [
+                'preview/flv_link',
+                {
+                    'uid': video_id,
+                },
+            ],
+        ]
+        r_json = json.dumps(r)
+        post = compat_urllib_parse.urlencode({'r': r_json})
+        req = compat_urllib_request.Request(self._API_URL, post)
+        req.add_header('Content-type', 'application/x-www-form-urlencoded')
+
+        response = self._download_json(req, video_id)
+        if response['status'] != 'OK':
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, response['data']),
+                expected=True
+            )
+        item = response['data'][0]
+        video_url = item['link']
+        duration = int_or_none(item['length'])
+        width = int_or_none(item['width'])
+        height = int_or_none(item['height'])
+        filesize = int_or_none(item['convert_size'])
+
+        formats = [{
+            'format_id': 'sd',
+            'http_headers': {'Range': 'bytes=0-'},  # Required to download
+            'url': video_url,
+            'width': width,
+            'height': height,
+            'filesize': filesize,
+        }]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'description': description,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/noco.py

@@ -5,7 +5,10 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    compat_urllib_request,
+    compat_urllib_parse,
     ExtractorError,
+    clean_html,
     unified_strdate,
     compat_str,
 )
@@ -13,6 +16,8 @@ from ..utils import (
 
 class NocoIE(InfoExtractor):
     _VALID_URL = r'http://(?:(?:www\.)?noco\.tv/emission/|player\.noco\.tv/\?idvideo=)(?P<id>\d+)'
+    _LOGIN_URL = 'http://noco.tv/do.php'
+    _NETRC_MACHINE = 'noco'
 
     _TEST = {
         'url': 'http://noco.tv/emission/11538/nolife/ami-ami-idol-hello-france/',
@@ -30,6 +35,28 @@ class NocoIE(InfoExtractor):
         'skip': 'Requires noco account',
     }
 
+    def _real_initialize(self):
+        self._login()
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+
+        login_form = {
+            'a': 'login',
+            'cookie': '1',
+            'username': username,
+            'password': password,
+        }
+        request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
+        request.add_header('Content-Type', 'application/x-www-form-urlencoded; charset=UTF-8')
+
+        login = self._download_json(request, None, 'Logging in as %s' % username)
+
+        if 'erreur' in login:
+            raise  ExtractorError('Unable to login: %s' % clean_html(login['erreur']), expected=True)
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')

youtube_dl/extractor/rutv.py

@@ -100,7 +100,7 @@ class RUTVIE(InfoExtractor):
             return mobj.group('url')
 
         mobj = re.search(
-            r'<meta[^>]+?property=(["\'])og:video\1[^>]+?content=(["\'])(?P<url>http://player\.(?:rutv\.ru|vgtrk\.com)/flash2v/container\.swf\?id=.+?\2)',
+            r'<meta[^>]+?property=(["\'])og:video\1[^>]+?content=(["\'])(?P<url>https?://player\.(?:rutv\.ru|vgtrk\.com)/flash2v/container\.swf\?id=.+?\2)',
             webpage)
         if mobj:
             return mobj.group('url')

youtube_dl/extractor/sharesix.py

@@ -0,0 +1,91 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    compat_urllib_request,
+    parse_duration,
+)
+
+
+class ShareSixIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?sharesix\.com/(?:f/)?(?P<id>[0-9a-zA-Z]+)'
+    _TESTS = [
+        {
+            'url': 'http://sharesix.com/f/OXjQ7Y6',
+            'md5': '9e8e95d8823942815a7d7c773110cc93',
+            'info_dict': {
+                'id': 'OXjQ7Y6',
+                'ext': 'mp4',
+                'title': 'big_buck_bunny_480p_surround-fix.avi',
+                'duration': 596,
+                'width': 854,
+                'height': 480,
+            },
+        },
+        {
+            'url': 'http://sharesix.com/lfrwoxp35zdd',
+            'md5': 'dd19f1435b7cec2d7912c64beeee8185',
+            'info_dict': {
+                'id': 'lfrwoxp35zdd',
+                'ext': 'flv',
+                'title': 'WhiteBoard___a_Mac_vs_PC_Parody_Cartoon.mp4.flv',
+                'duration': 65,
+                'width': 1280,
+                'height': 720,
+            },
+        }
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        fields = {
+            'method_free': 'Free'
+        }
+        post = compat_urllib_parse.urlencode(fields)
+        req = compat_urllib_request.Request(url, post)
+        req.add_header('Content-type', 'application/x-www-form-urlencoded')
+
+        webpage = self._download_webpage(req, video_id,
+                                         'Downloading video page')
+
+        video_url = self._search_regex(
+            r"var\slnk1\s=\s'([^']+)'", webpage, 'video URL')
+        title = self._html_search_regex(
+            r'(?s)<dt>Filename:</dt>.+?<dd>(.+?)</dd>', webpage, 'title')
+        duration = parse_duration(
+            self._search_regex(
+                r'(?s)<dt>Length:</dt>.+?<dd>(.+?)</dd>',
+                webpage,
+                'duration',
+                fatal=False
+            )
+        )
+
+        m = re.search(
+            r'''(?xs)<dt>Width\sx\sHeight</dt>.+?
+                     <dd>(?P<width>\d+)\sx\s(?P<height>\d+)</dd>''',
+            webpage
+        )
+        width = height = None
+        if m:
+            width, height = int(m.group('width')), int(m.group('height'))
+
+        formats = [{
+            'format_id': 'sd',
+            'url': video_url,
+            'width': width,
+            'height': height,
+        }]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/vgtv.py

@@ -0,0 +1,119 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import float_or_none
+
+
+class VGTVIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?vgtv\.no/#!/(?:.*)/(?P<id>[0-9]+)'
+    _TESTS = [
+        {
+            # streamType: vod
+            'url': 'http://www.vgtv.no/#!/video/84196/hevnen-er-soet-episode-10-abu',
+            'md5': 'b8be7a234cebb840c0d512c78013e02f',
+            'info_dict': {
+                'id': '84196',
+                'ext': 'mp4',
+                'title': 'Hevnen er søt episode 10: Abu',
+                'description': 'md5:e25e4badb5f544b04341e14abdc72234',
+                'thumbnail': 're:^https?://.*\.jpg',
+                'duration': 648.000,
+                'timestamp': 1404626400,
+                'upload_date': '20140706',
+                'view_count': int,
+            },
+        },
+        {
+            # streamType: wasLive
+            'url': 'http://www.vgtv.no/#!/live/100764/opptak-vgtv-foelger-em-kvalifiseringen',
+            'info_dict': {
+                'id': '100764',
+                'ext': 'mp4',
+                'title': 'OPPTAK: VGTV følger EM-kvalifiseringen',
+                'description': 'md5:3772d9c0dc2dff92a886b60039a7d4d3',
+                'thumbnail': 're:^https?://.*\.jpg',
+                'duration': 9056.000,
+                'timestamp': 1410113864,
+                'upload_date': '20140907',
+                'view_count': int,
+            },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
+        },
+        {
+            # streamType: live
+            'url': 'http://www.vgtv.no/#!/live/100015/direkte-her-kan-du-se-laksen-live-fra-suldalslaagen',
+            'info_dict': {
+                'id': '100015',
+                'ext': 'mp4',
+                'title': 'DIREKTE: Her kan du se laksen live fra Suldalslågen!',
+                'description': 'md5:9a60cc23fa349f761628924e56eeec2d',
+                'thumbnail': 're:^https?://.*\.jpg',
+                'duration': 0,
+                'timestamp': 1407423348,
+                'upload_date': '20140807',
+                'view_count': int,
+            },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        data = self._download_json(
+            'http://svp.vg.no/svp/api/v1/vgtv/assets/%s?appName=vgtv-website' % video_id,
+            video_id, 'Downloading media JSON')
+
+        streams = data['streamUrls']
+
+        formats = []
+
+        hls_url = streams.get('hls')
+        if hls_url:
+            formats.extend(self._extract_m3u8_formats(hls_url, video_id, 'mp4'))
+
+        hds_url = streams.get('hds')
+        if hds_url:
+            formats.extend(self._extract_f4m_formats(hds_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18', video_id))
+
+        mp4_url = streams.get('mp4')
+        if mp4_url:
+            _url = hls_url or hds_url
+            MP4_URL_TEMPLATE = '%s/%%s.%s' % (mp4_url.rpartition('/')[0], mp4_url.rpartition('.')[-1])
+            for mp4_format in _url.split(','):
+                m = re.search('(?P<width>\d+)_(?P<height>\d+)_(?P<vbr>\d+)', mp4_format)
+                if not m:
+                    continue
+                width = int(m.group('width'))
+                height = int(m.group('height'))
+                vbr = int(m.group('vbr'))
+                formats.append({
+                    'url': MP4_URL_TEMPLATE % mp4_format,
+                    'format_id': 'mp4-%s' % vbr,
+                    'width': width,
+                    'height': height,
+                    'vbr': vbr,
+                    'preference': 1,
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': data['title'],
+            'description': data['description'],
+            'thumbnail': data['images']['main'] + '?t[]=900x506q80',
+            'timestamp': data['published'],
+            'duration': float_or_none(data['duration'], 1000),
+            'view_count': data['displays'],
+            'formats': formats,
+        }

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2014.09.06'
+__version__ = '2014.09.10'