Update upstream source from tag 'upstream/2020.06.16'

[youtubedl] / youtube_dl / extractor / noco.py

diff --git a/youtube_dl/extractor/noco.py b/youtube_dl/extractor/noco.py
index 664dc81d47ce7af613636022f4e540dffd67f8b6..30df905af294cae536710ccce596b30f0a80e117 100644 (file)
--- a/youtube_dl/extractor/noco.py
+++ b/youtube_dl/extractor/noco.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


@@ -8,8 +8,7 @@ import hashlib
 from .common import InfoExtractor
 from ..compat import (
     compat_str,
 from .common import InfoExtractor
 from ..compat import (
     compat_str,

-    compat_urllib_parse,
-    compat_urllib_request,
+    compat_urlparse,

 )
 from ..utils import (
     clean_html,
 )
 from ..utils import (
     clean_html,


@@ -17,12 +16,14 @@ from ..utils import (
     int_or_none,
     float_or_none,
     parse_iso8601,
     int_or_none,
     float_or_none,
     parse_iso8601,

+    sanitized_Request,
+    urlencode_postdata,

 )
 
 
 class NocoIE(InfoExtractor):
 )
 
 
 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'
+    _VALID_URL = r'https?://(?:(?:www\.)?noco\.tv/emission/|player\.noco\.tv/\?idvideo=)(?P<id>\d+)'
+    _LOGIN_URL = 'https://noco.tv/do.php'

     _API_URL_TEMPLATE = 'https://api.noco.tv/1.1/%s?ts=%s&tk=%s'
     _SUB_LANG_TEMPLATE = '&sub_lang=%s'
     _NETRC_MACHINE = 'noco'
     _API_URL_TEMPLATE = 'https://api.noco.tv/1.1/%s?ts=%s&tk=%s'
     _SUB_LANG_TEMPLATE = '&sub_lang=%s'
     _NETRC_MACHINE = 'noco'


@@ -64,32 +65,40 @@ class NocoIE(InfoExtractor):
         self._login()
 
     def _login(self):
         self._login()
 
     def _login(self):

-        (username, password) = self._get_login_info()
+        username, password = self._get_login_info()

         if username is None:
             return
 
         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)
+        login = self._download_json(
+            self._LOGIN_URL, None, 'Logging in',
+            data=urlencode_postdata({
+                'a': 'login',
+                'cookie': '1',
+                'username': username,
+                'password': password,
+            }),
+            headers={
+                'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
+            })

 
         if 'erreur' in login:
             raise ExtractorError('Unable to login: %s' % clean_html(login['erreur']), expected=True)
 
 
         if 'erreur' in login:
             raise ExtractorError('Unable to login: %s' % clean_html(login['erreur']), expected=True)
 

+    @staticmethod
+    def _ts():
+        return int(time.time() * 1000)
+

     def _call_api(self, path, video_id, note, sub_lang=None):
     def _call_api(self, path, video_id, note, sub_lang=None):

-        ts = compat_str(int(time.time() * 1000))
+        ts = compat_str(self._ts() + self._ts_offset)

         tk = hashlib.md5((hashlib.md5(ts.encode('ascii')).hexdigest() + '#8S?uCraTedap6a').encode('ascii')).hexdigest()
         url = self._API_URL_TEMPLATE % (path, ts, tk)
         if sub_lang:
             url += self._SUB_LANG_TEMPLATE % sub_lang
 
         tk = hashlib.md5((hashlib.md5(ts.encode('ascii')).hexdigest() + '#8S?uCraTedap6a').encode('ascii')).hexdigest()
         url = self._API_URL_TEMPLATE % (path, ts, tk)
         if sub_lang:
             url += self._SUB_LANG_TEMPLATE % sub_lang
 

-        resp = self._download_json(url, video_id, note)
+        request = sanitized_Request(url)
+        request.add_header('Referer', self._referer)
+
+        resp = self._download_json(request, video_id, note)

 
         if isinstance(resp, dict) and resp.get('error'):
             self._raise_error(resp['error'], resp['description'])
 
         if isinstance(resp, dict) and resp.get('error'):
             self._raise_error(resp['error'], resp['description'])


@@ -102,8 +111,22 @@ class NocoIE(InfoExtractor):
             expected=True)
 
     def _real_extract(self, url):
             expected=True)
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
+
+        # Timestamp adjustment offset between server time and local time
+        # must be calculated in order to use timestamps closest to server's
+        # in all API requests (see https://github.com/ytdl-org/youtube-dl/issues/7864)
+        webpage = self._download_webpage(url, video_id)
+
+        player_url = self._search_regex(
+            r'(["\'])(?P<player>https?://noco\.tv/(?:[^/]+/)+NocoPlayer.+?\.swf.*?)\1',
+            webpage, 'noco player', group='player',
+            default='http://noco.tv/cdata/js/player/NocoPlayer-v1.2.40.swf')
+
+        qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(player_url).query)
+        ts = int_or_none(qs.get('ts', [None])[0])
+        self._ts_offset = ts - self._ts() if ts else 0
+        self._referer = player_url

 
         medias = self._call_api(
             'shows/%s/medias' % video_id,
 
         medias = self._call_api(
             'shows/%s/medias' % video_id,


@@ -155,8 +178,8 @@ class NocoIE(InfoExtractor):
                         'format_id': format_id_extended,
                         'width': int_or_none(fmt.get('res_width')),
                         'height': int_or_none(fmt.get('res_lines')),
                         'format_id': format_id_extended,
                         'width': int_or_none(fmt.get('res_width')),
                         'height': int_or_none(fmt.get('res_lines')),

-                        'abr': int_or_none(fmt.get('audiobitrate')),
-                        'vbr': int_or_none(fmt.get('videobitrate')),
+                        'abr': int_or_none(fmt.get('audiobitrate'), 1000),
+                        'vbr': int_or_none(fmt.get('videobitrate'), 1000),

                         'filesize': int_or_none(fmt.get('filesize')),
                         'format_note': qualities[format_id].get('quality_name'),
                         'quality': qualities[format_id].get('priority'),
                         'filesize': int_or_none(fmt.get('filesize')),
                         'format_note': qualities[format_id].get('quality_name'),
                         'quality': qualities[format_id].get('priority'),


@@ -166,6 +189,10 @@ class NocoIE(InfoExtractor):
         self._sort_formats(formats)
 
         timestamp = parse_iso8601(show.get('online_date_start_utc'), ' ')
         self._sort_formats(formats)
 
         timestamp = parse_iso8601(show.get('online_date_start_utc'), ' ')

+
+        if timestamp is not None and timestamp < 0:
+            timestamp = None
+

         uploader = show.get('partner_name')
         uploader_id = show.get('partner_key')
         duration = float_or_none(show.get('duration_ms'), 1000)
         uploader = show.get('partner_name')
         uploader_id = show.get('partner_key')
         duration = float_or_none(show.get('duration_ms'), 1000)


@@ -191,7 +218,7 @@ class NocoIE(InfoExtractor):
         if episode_number:
             title += ' #' + compat_str(episode_number)
         if episode:
         if episode_number:
             title += ' #' + compat_str(episode_number)
         if episode:

-            title += ' - ' + episode
+            title += ' - ' + compat_str(episode)

 
         description = show.get('show_resume') or show.get('family_resume')
 
 
         description = show.get('show_resume') or show.get('family_resume')