Prepare to upload

[youtubedl] / youtube_dl / extractor / smotri.py

diff --git a/youtube_dl/extractor/smotri.py b/youtube_dl/extractor/smotri.py
index 0751efc6111c96ca1c089c66183429f9bde6147c..370fa887968128281a6286f78a1fdf4bf59f7b9f 100644 (file)
--- a/youtube_dl/extractor/smotri.py
+++ b/youtube_dl/extractor/smotri.py
@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8

 from __future__ import unicode_literals
 
 import re
 from __future__ import unicode_literals
 
 import re


@@ -8,25 +8,26 @@ import uuid
 
 from .common import InfoExtractor
 from ..utils import (
 
 from .common import InfoExtractor
 from ..utils import (

-    compat_urllib_parse,
-    compat_urllib_request,

     ExtractorError,
     int_or_none,
     ExtractorError,
     int_or_none,

+    sanitized_Request,

     unified_strdate,
     unified_strdate,

+    urlencode_postdata,
+    xpath_text,

 )
 
 
 class SmotriIE(InfoExtractor):
     IE_DESC = 'Smotri.com'
     IE_NAME = 'smotri'
 )
 
 
 class SmotriIE(InfoExtractor):
     IE_DESC = 'Smotri.com'
     IE_NAME = 'smotri'

-    _VALID_URL = r'^https?://(?:www\.)?(?:smotri\.com/video/view/\?id=|pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=)(?P<id>v(?P<realvideoid>[0-9]+)[a-z0-9]{4})'
+    _VALID_URL = r'https?://(?:www\.)?(?:smotri\.com/video/view/\?id=|pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=)(?P<id>v(?P<realvideoid>[0-9]+)[a-z0-9]{4})'

     _NETRC_MACHINE = 'smotri'
 
     _TESTS = [
         # real video id 2610366
         {
             'url': 'http://smotri.com/video/view/?id=v261036632ab',
     _NETRC_MACHINE = 'smotri'
 
     _TESTS = [
         # real video id 2610366
         {
             'url': 'http://smotri.com/video/view/?id=v261036632ab',

-            'md5': '2a7b08249e6f5636557579c368040eb9',
+            'md5': '02c0dfab2102984e9c5bb585cc7cc321',

             'info_dict': {
                 'id': 'v261036632ab',
                 'ext': 'mp4',
             'info_dict': {
                 'id': 'v261036632ab',
                 'ext': 'mp4',


@@ -51,7 +52,7 @@ class SmotriIE(InfoExtractor):
                 'thumbnail': 'http://frame4.loadup.ru/03/ed/57591.2.3.jpg',
             },
         },
                 'thumbnail': 'http://frame4.loadup.ru/03/ed/57591.2.3.jpg',
             },
         },

-        # video-password
+        # video-password, not approved by moderator

         {
             'url': 'http://smotri.com/video/view/?id=v1390466a13c',
             'md5': 'f6331cef33cad65a0815ee482a54440b',
         {
             'url': 'http://smotri.com/video/view/?id=v1390466a13c',
             'md5': 'f6331cef33cad65a0815ee482a54440b',


@@ -67,8 +68,26 @@ class SmotriIE(InfoExtractor):
             'params': {
                 'videopassword': 'qwerty',
             },
             'params': {
                 'videopassword': 'qwerty',
             },

+            'skip': 'Video is not approved by moderator',

         },
         },

-        # age limit + video-password
+        # video-password
+        {
+            'url': 'http://smotri.com/video/view/?id=v6984858774#',
+            'md5': 'f11e01d13ac676370fc3b95b9bda11b0',
+            'info_dict': {
+                'id': 'v6984858774',
+                'ext': 'mp4',
+                'title': 'Дача Солженицина ПАРОЛЬ 223322',
+                'uploader': 'psavari1',
+                'uploader_id': 'psavari1',
+                'upload_date': '20081103',
+                'thumbnail': r're:^https?://.*\.jpg$',
+            },
+            'params': {
+                'videopassword': '223322',
+            },
+        },
+        # age limit + video-password, not approved by moderator

         {
             'url': 'http://smotri.com/video/view/?id=v15408898bcf',
             'md5': '91e909c9f0521adf5ee86fbe073aad70',
         {
             'url': 'http://smotri.com/video/view/?id=v15408898bcf',
             'md5': '91e909c9f0521adf5ee86fbe073aad70',


@@ -84,12 +103,31 @@ class SmotriIE(InfoExtractor):
             },
             'params': {
                 'videopassword': '333'
             },
             'params': {
                 'videopassword': '333'

-            }
+            },
+            'skip': 'Video is not approved by moderator',
+        },
+        # age limit + video-password
+        {
+            'url': 'http://smotri.com/video/view/?id=v7780025814',
+            'md5': 'b4599b068422559374a59300c5337d72',
+            'info_dict': {
+                'id': 'v7780025814',
+                'ext': 'mp4',
+                'title': 'Sexy Beach (пароль 123)',
+                'uploader': 'вАся',
+                'uploader_id': 'asya_prosto',
+                'upload_date': '20081218',
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'age_limit': 18,
+            },
+            'params': {
+                'videopassword': '123'
+            },

         },
         # swf player
         {
             'url': 'http://pics.smotri.com/scrubber_custom8.swf?file=v9188090500',
         },
         # swf player
         {
             'url': 'http://pics.smotri.com/scrubber_custom8.swf?file=v9188090500',

-            'md5': '4d47034979d9390d14acdf59c4935bc2',
+            'md5': '31099eeb4bc906712c5f40092045108d',

             'info_dict': {
                 'id': 'v9188090500',
                 'ext': 'mp4',
             'info_dict': {
                 'id': 'v9188090500',
                 'ext': 'mp4',


@@ -120,9 +158,6 @@ class SmotriIE(InfoExtractor):
     def _search_meta(self, name, html, display_name=None):
         if display_name is None:
             display_name = name
     def _search_meta(self, name, html, display_name=None):
         if display_name is None:
             display_name = name

-        return self._html_search_regex(
-            r'<meta itemprop="%s" content="([^"]+)" />' % re.escape(name),
-            html, display_name, fatal=False)

         return self._html_search_meta(name, html, display_name)
 
     def _real_extract(self, url):
         return self._html_search_meta(name, html, display_name)
 
     def _real_extract(self, url):


@@ -136,25 +171,37 @@ class SmotriIE(InfoExtractor):
             'getvideoinfo': '1',
         }
 
             'getvideoinfo': '1',
         }
 

-        request = compat_urllib_request.Request(
-            'http://smotri.com/video/view/url/bot/', compat_urllib_parse.urlencode(video_form))
-        request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        video_password = self._downloader.params.get('videopassword')
+        if video_password:
+            video_form['pass'] = hashlib.md5(video_password.encode('utf-8')).hexdigest()

 
 

-        video = self._download_json(request, video_id, 'Downloading video JSON')
+        video = self._download_json(
+            'http://smotri.com/video/view/url/bot/',
+            video_id, 'Downloading video JSON',
+            data=urlencode_postdata(video_form),
+            headers={'Content-Type': 'application/x-www-form-urlencoded'})

 
 

-        if video.get('_moderate_no') or not video.get('moderated'):
-            raise ExtractorError('Video %s has not been approved by moderator' % video_id, expected=True)
+        video_url = video.get('_vidURL') or video.get('_vidURL_mp4')

 
 

-        if video.get('error'):
-            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+        if not video_url:
+            if video.get('_moderate_no'):
+                raise ExtractorError(
+                    'Video %s has not been approved by moderator' % video_id, expected=True)
+
+            if video.get('error'):
+                raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+
+            if video.get('_pass_protected') == 1:
+                msg = ('Invalid video password' if video_password
+                       else 'This video is protected by a password, use the --video-password option')
+                raise ExtractorError(msg, expected=True)

 
 

-        video_url = video.get('_vidURL') or video.get('_vidURL_mp4')

         title = video['title']
         title = video['title']

-        thumbnail = video['_imgURL']
-        upload_date = unified_strdate(video['added'])
-        uploader = video['userNick']
-        uploader_id = video['userLogin']
-        duration = int_or_none(video['duration'])
+        thumbnail = video.get('_imgURL')
+        upload_date = unified_strdate(video.get('added'))
+        uploader = video.get('userNick')
+        uploader_id = video.get('userLogin')
+        duration = int_or_none(video.get('duration'))

 
         # Video JSON does not provide enough meta data
         # We will extract some from the video web page instead
 
         # Video JSON does not provide enough meta data
         # We will extract some from the video web page instead


@@ -163,7 +210,7 @@ class SmotriIE(InfoExtractor):
 
         # Warning if video is unavailable
         warning = self._html_search_regex(
 
         # Warning if video is unavailable
         warning = self._html_search_regex(

-            r'<div class="videoUnModer">(.*?)</div>', webpage,
+            r'<div[^>]+class="videoUnModer"[^>]*>(.+?)</div>', webpage,

             'warning message', default=None)
         if warning is not None:
             self._downloader.report_warning(
             'warning message', default=None)
         if warning is not None:
             self._downloader.report_warning(


@@ -171,20 +218,22 @@ class SmotriIE(InfoExtractor):
                 (video_id, warning))
 
         # Adult content
                 (video_id, warning))
 
         # Adult content

-        if re.search('EroConfirmText">', webpage) is not None:
+        if 'EroConfirmText">' in webpage:

             self.report_age_confirmation()
             confirm_string = self._html_search_regex(
             self.report_age_confirmation()
             confirm_string = self._html_search_regex(

-                r'<a href="/video/view/\?id=%s&confirm=([^"]+)" title="[^"]+">' % video_id,
+                r'<a[^>]+href="/video/view/\?id=%s&confirm=([^"]+)"' % video_id,

                 webpage, 'confirm string')
             confirm_url = webpage_url + '&confirm=%s' % confirm_string
                 webpage, 'confirm string')
             confirm_url = webpage_url + '&confirm=%s' % confirm_string

-            webpage = self._download_webpage(confirm_url, video_id, 'Downloading video page (age confirmed)')
+            webpage = self._download_webpage(
+                confirm_url, video_id,
+                'Downloading video page (age confirmed)')

             adult_content = True
         else:
             adult_content = False
 
         view_count = self._html_search_regex(
             adult_content = True
         else:
             adult_content = False
 
         view_count = self._html_search_regex(

-            'Общее количество просмотров.*?<span class="Number">(\\d+)</span>',
-            webpage, 'view count', fatal=False, flags=re.MULTILINE | re.DOTALL)
+            r'(?s)Общее количество просмотров.*?<span class="Number">(\d+)</span>',
+            webpage, 'view count', fatal=False)

 
         return {
             'id': video_id,
 
         return {
             'id': video_id,


@@ -203,37 +252,33 @@ class SmotriIE(InfoExtractor):
 class SmotriCommunityIE(InfoExtractor):
     IE_DESC = 'Smotri.com community videos'
     IE_NAME = 'smotri:community'
 class SmotriCommunityIE(InfoExtractor):
     IE_DESC = 'Smotri.com community videos'
     IE_NAME = 'smotri:community'

-    _VALID_URL = r'^https?://(?:www\.)?smotri\.com/community/video/(?P<communityid>[0-9A-Za-z_\'-]+)'
+    _VALID_URL = r'https?://(?:www\.)?smotri\.com/community/video/(?P<id>[0-9A-Za-z_\'-]+)'

     _TEST = {
         'url': 'http://smotri.com/community/video/kommuna',
         'info_dict': {
             'id': 'kommuna',
     _TEST = {
         'url': 'http://smotri.com/community/video/kommuna',
         'info_dict': {
             'id': 'kommuna',

-            'title': 'КПРФ',

         },
         'playlist_mincount': 4,
     }
 
     def _real_extract(self, url):
         },
         'playlist_mincount': 4,
     }
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        community_id = mobj.group('communityid')
+        community_id = self._match_id(url)

 
 

-        url = 'http://smotri.com/export/rss/video/by/community/-/%s/video.xml' % community_id
-        rss = self._download_xml(url, community_id, 'Downloading community RSS')
+        rss = self._download_xml(
+            'http://smotri.com/export/rss/video/by/community/-/%s/video.xml' % community_id,
+            community_id, 'Downloading community RSS')

 
 

-        entries = [self.url_result(video_url.text, 'Smotri')
-                   for video_url in rss.findall('./channel/item/link')]
-
-        description_text = rss.find('./channel/description').text
-        community_title = self._html_search_regex(
-            '^Видео сообщества "([^"]+)"$', description_text, 'community title')
+        entries = [
+            self.url_result(video_url.text, SmotriIE.ie_key())
+            for video_url in rss.findall('./channel/item/link')]

 
 

-        return self.playlist_result(entries, community_id, community_title)
+        return self.playlist_result(entries, community_id)

 
 
 class SmotriUserIE(InfoExtractor):
     IE_DESC = 'Smotri.com user videos'
     IE_NAME = 'smotri:user'
 
 
 class SmotriUserIE(InfoExtractor):
     IE_DESC = 'Smotri.com user videos'
     IE_NAME = 'smotri:user'

-    _VALID_URL = r'^https?://(?:www\.)?smotri\.com/user/(?P<userid>[0-9A-Za-z_\'-]+)'
+    _VALID_URL = r'https?://(?:www\.)?smotri\.com/user/(?P<id>[0-9A-Za-z_\'-]+)'

     _TESTS = [{
         'url': 'http://smotri.com/user/inspector',
         'info_dict': {
     _TESTS = [{
         'url': 'http://smotri.com/user/inspector',
         'info_dict': {


@@ -244,19 +289,19 @@ class SmotriUserIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
     }]
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        user_id = mobj.group('userid')
+        user_id = self._match_id(url)

 
 

-        url = 'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id
-        rss = self._download_xml(url, user_id, 'Downloading user RSS')
+        rss = self._download_xml(
+            'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id,
+            user_id, 'Downloading user RSS')

 
         entries = [self.url_result(video_url.text, 'Smotri')
                    for video_url in rss.findall('./channel/item/link')]
 
 
         entries = [self.url_result(video_url.text, 'Smotri')
                    for video_url in rss.findall('./channel/item/link')]
 

-        description_text = rss.find('./channel/description').text
-        user_nickname = self._html_search_regex(
-            '^Видео режиссера (.*)$', description_text,
-            'user nickname')
+        description_text = xpath_text(rss, './channel/description') or ''
+        user_nickname = self._search_regex(
+            '^Видео режиссера (.+)$', description_text,
+            'user nickname', fatal=False)

 
         return self.playlist_result(entries, user_id, user_nickname)
 
 
         return self.playlist_result(entries, user_id, user_nickname)
 


@@ -264,25 +309,26 @@ class SmotriUserIE(InfoExtractor):
 class SmotriBroadcastIE(InfoExtractor):
     IE_DESC = 'Smotri.com broadcasts'
     IE_NAME = 'smotri:broadcast'
 class SmotriBroadcastIE(InfoExtractor):
     IE_DESC = 'Smotri.com broadcasts'
     IE_NAME = 'smotri:broadcast'

-    _VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/live/(?P<broadcastid>[^/]+))/?.*'
+    _VALID_URL = r'https?://(?:www\.)?(?P<url>smotri\.com/live/(?P<id>[^/]+))/?.*'

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

-        broadcast_id = mobj.group('broadcastid')
+        broadcast_id = mobj.group('id')

 
         broadcast_url = 'http://' + mobj.group('url')
         broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page')
 
         if re.search('>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None:
 
         broadcast_url = 'http://' + mobj.group('url')
         broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page')
 
         if re.search('>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None:

-            raise ExtractorError('Broadcast %s does not exist' % broadcast_id, expected=True)
+            raise ExtractorError(
+                'Broadcast %s does not exist' % broadcast_id, expected=True)

 
         # Adult content
         if re.search('EroConfirmText">', broadcast_page) is not None:
 
             (username, password) = self._get_login_info()
             if username is None:
 
         # Adult content
         if re.search('EroConfirmText">', broadcast_page) is not None:
 
             (username, password) = self._get_login_info()
             if username is None:

-                raise ExtractorError('Erotic broadcasts allowed only for registered users, '
-                                     'use --username and --password options to provide account credentials.', expected=True)
+                self.raise_login_required(
+                    'Erotic broadcasts allowed only for registered users')

 
             login_form = {
                 'login-hint53': '1',
 
             login_form = {
                 'login-hint53': '1',


@@ -291,50 +337,58 @@ class SmotriBroadcastIE(InfoExtractor):
                 'password': password,
             }
 
                 'password': password,
             }
 

-            request = compat_urllib_request.Request(broadcast_url + '/?no_redirect=1', compat_urllib_parse.urlencode(login_form))
+            request = sanitized_Request(
+                broadcast_url + '/?no_redirect=1', urlencode_postdata(login_form))

             request.add_header('Content-Type', 'application/x-www-form-urlencoded')
             request.add_header('Content-Type', 'application/x-www-form-urlencoded')

-            broadcast_page = self._download_webpage(request, broadcast_id, 'Logging in and confirming age')
+            broadcast_page = self._download_webpage(
+                request, broadcast_id, 'Logging in and confirming age')

 
 

-            if re.search('>Неверный логин или пароль<', broadcast_page) is not None:
-                raise ExtractorError('Unable to log in: bad username or password', expected=True)
+            if '>Неверный логин или пароль<' in broadcast_page:
+                raise ExtractorError(
+                    'Unable to log in: bad username or password', expected=True)

 
             adult_content = True
         else:
             adult_content = False
 
         ticket = self._html_search_regex(
 
             adult_content = True
         else:
             adult_content = False
 
         ticket = self._html_search_regex(

-            'window\.broadcast_control\.addFlashVar\\(\'file\', \'([^\']+)\'\\);',
+            r"window\.broadcast_control\.addFlashVar\('file'\s*,\s*'([^']+)'\)",

             broadcast_page, 'broadcast ticket')
 
         url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket
 
             broadcast_page, 'broadcast ticket')
 
         url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket
 

-        broadcast_password = self._downloader.params.get('videopassword', None)
+        broadcast_password = self._downloader.params.get('videopassword')

         if broadcast_password:
             url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest()
 
         if broadcast_password:
             url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest()
 

-        broadcast_json_page = self._download_webpage(url, broadcast_id, 'Downloading broadcast JSON')
+        broadcast_json_page = self._download_webpage(
+            url, broadcast_id, 'Downloading broadcast JSON')

 
         try:
             broadcast_json = json.loads(broadcast_json_page)
 
             protected_broadcast = broadcast_json['_pass_protected'] == 1
             if protected_broadcast and not broadcast_password:
 
         try:
             broadcast_json = json.loads(broadcast_json_page)
 
             protected_broadcast = broadcast_json['_pass_protected'] == 1
             if protected_broadcast and not broadcast_password:

-                raise ExtractorError('This broadcast is protected by a password, use the --video-password option', expected=True)
+                raise ExtractorError(
+                    'This broadcast is protected by a password, use the --video-password option',
+                    expected=True)

 
             broadcast_offline = broadcast_json['is_play'] == 0
             if broadcast_offline:
                 raise ExtractorError('Broadcast %s is offline' % broadcast_id, expected=True)
 
             rtmp_url = broadcast_json['_server']
 
             broadcast_offline = broadcast_json['is_play'] == 0
             if broadcast_offline:
                 raise ExtractorError('Broadcast %s is offline' % broadcast_id, expected=True)
 
             rtmp_url = broadcast_json['_server']

-            if not rtmp_url.startswith('rtmp://'):
+            mobj = re.search(r'^rtmp://[^/]+/(?P<app>.+)/?$', rtmp_url)
+            if not mobj:

                 raise ExtractorError('Unexpected broadcast rtmp URL')
 
             broadcast_playpath = broadcast_json['_streamName']
                 raise ExtractorError('Unexpected broadcast rtmp URL')
 
             broadcast_playpath = broadcast_json['_streamName']

-            broadcast_thumbnail = broadcast_json['_imgURL']
-            broadcast_title = broadcast_json['title']
-            broadcast_description = broadcast_json['description']
-            broadcaster_nick = broadcast_json['nick']
-            broadcaster_login = broadcast_json['login']
+            broadcast_app = '%s/%s' % (mobj.group('app'), broadcast_json['_vidURL'])
+            broadcast_thumbnail = broadcast_json.get('_imgURL')
+            broadcast_title = self._live_title(broadcast_json['title'])
+            broadcast_description = broadcast_json.get('description')
+            broadcaster_nick = broadcast_json.get('nick')
+            broadcaster_login = broadcast_json.get('login')

             rtmp_conn = 'S:%s' % uuid.uuid4().hex
         except KeyError:
             if protected_broadcast:
             rtmp_conn = 'S:%s' % uuid.uuid4().hex
         except KeyError:
             if protected_broadcast:


@@ -352,6 +406,9 @@ class SmotriBroadcastIE(InfoExtractor):
             'age_limit': 18 if adult_content else 0,
             'ext': 'flv',
             'play_path': broadcast_playpath,
             'age_limit': 18 if adult_content else 0,
             'ext': 'flv',
             'play_path': broadcast_playpath,

+            'player_url': 'http://pics.smotri.com/broadcast_play.swf',
+            'app': broadcast_app,

             'rtmp_live': True,
             'rtmp_live': True,

-            'rtmp_conn': rtmp_conn
+            'rtmp_conn': rtmp_conn,
+            'is_live': True,

         }
         }