Fix "invalid escape sequences" error on Python 3.6

[youtube-dl] / youtube_dl / extractor / nova.py

diff --git a/youtube_dl/extractor/nova.py b/youtube_dl/extractor/nova.py
index 10957e5fa2c7f5674632907875033632b3144018..06cb8cb3f5a867104a8bd67abd9ce60bbc1df25f 100644 (file)
--- a/youtube_dl/extractor/nova.py
+++ b/youtube_dl/extractor/nova.py
@@ -1,31 +1,34 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
-from ..utils import clean_html, determine_ext
+from ..utils import (
+    clean_html,
+    unified_strdate,
+)
 
 
 class NovaIE(InfoExtractor):
     IE_DESC = 'TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz'
-    _VALID_URL = 'http://(?:[^.]+\.)?(?P<site>tv(?:noviny)?|tn|novaplus|vymena|fanda|krasna|doma|prask)\.nova\.cz/(?:[^/]+/)+(?P<id>[^/]+?)(?:\.html|/?)$'
+    _VALID_URL = r'https?://(?:[^.]+\.)?(?P<site>tv(?:noviny)?|tn|novaplus|vymena|fanda|krasna|doma|prask)\.nova\.cz/(?:[^/]+/)+(?P<id>[^/]+?)(?:\.html|/|$)'
     _TESTS = [{
-        'url': 'http://tvnoviny.nova.cz/clanek/novinky/co-na-sebe-sportaci-praskli-vime-jestli-pujde-hrdlicka-na-materskou.html',
+        'url': 'http://tvnoviny.nova.cz/clanek/novinky/co-na-sebe-sportaci-praskli-vime-jestli-pujde-hrdlicka-na-materskou.html?utm_source=tvnoviny&utm_medium=cpfooter&utm_campaign=novaplus',
         'info_dict': {
             'id': '1608920',
             'display_id': 'co-na-sebe-sportaci-praskli-vime-jestli-pujde-hrdlicka-na-materskou',
             'ext': 'flv',
             'title': 'Duel: Michal Hrdlička a Petr Suchoň',
             'description': 'md5:d0cc509858eee1b1374111c588c6f5d5',
-            'thumbnail': 're:^https?://.*\.(?:jpg)',
+            'thumbnail': r're:^https?://.*\.(?:jpg)',
         },
         'params': {
             # rtmp download
             'skip_download': True,
         }
     }, {
-        'url': 'http://tn.nova.cz/clanek/tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci.html',
+        'url': 'http://tn.nova.cz/clanek/tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci.html#player_13260',
         'md5': '1dd7b9d5ea27bc361f110cd855a19bd3',
         'info_dict': {
             'id': '1757139',
@@ -33,17 +36,17 @@ class NovaIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Podzemní nemocnice v pražské Krči',
             'description': 'md5:f0a42dd239c26f61c28f19e62d20ef53',
-            'thumbnail': 're:^https?://.*\.(?:jpg)',
+            'thumbnail': r're:^https?://.*\.(?:jpg)',
         }
     }, {
-        'url': 'http://novaplus.nova.cz/porad/policie-modrava/video/5591-policie-modrava-15-dil-blondynka-na-hrbitove/',
+        'url': 'http://novaplus.nova.cz/porad/policie-modrava/video/5591-policie-modrava-15-dil-blondynka-na-hrbitove',
         'info_dict': {
             'id': '1756825',
             'display_id': '5591-policie-modrava-15-dil-blondynka-na-hrbitove',
-            'ext': 'mp4',
+            'ext': 'flv',
             'title': 'Policie Modrava - 15. díl - Blondýnka na hřbitově',
-            'description': 'md5:dc24e50be5908df83348e50d1431295e',
-            'thumbnail': 're:^https?://.*\.(?:jpg)',
+            'description': 'md5:dc24e50be5908df83348e50d1431295e',  # Make sure this description is clean of html tags
+            'thumbnail': r're:^https?://.*\.(?:jpg)',
         },
         'params': {
             # rtmp download
@@ -53,9 +56,9 @@ class NovaIE(InfoExtractor):
         'url': 'http://novaplus.nova.cz/porad/televizni-noviny/video/5585-televizni-noviny-30-5-2015/',
         'info_dict': {
             'id': '1756858',
-            'ext': 'mp4',
+            'ext': 'flv',
             'title': 'Televizní noviny - 30. 5. 2015',
-            'thumbnail': 're:^https?://.*\.(?:jpg)',
+            'thumbnail': r're:^https?://.*\.(?:jpg)',
             'upload_date': '20150530',
         },
         'params': {
@@ -69,7 +72,7 @@ class NovaIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Zaklínač 3: Divoký hon',
             'description': 're:.*Pokud se stejně jako my nemůžete.*',
-            'thumbnail': 're:https?://.*\.jpg(\?.*)?',
+            'thumbnail': r're:https?://.*\.jpg(\?.*)?',
             'upload_date': '20150521',
         },
         'params': {
@@ -136,21 +139,32 @@ class NovaIE(InfoExtractor):
 
         mediafile = config['mediafile']
         video_url = mediafile['src']
-        ext = determine_ext(video_url)
-        video_url = video_url.replace('&{}:'.format(ext), '')
+
+        m = re.search(r'^(?P<url>rtmpe?://[^/]+/(?P<app>[^/]+?))/&*(?P<playpath>.+)$', video_url)
+        if m:
+            formats = [{
+                'url': m.group('url'),
+                'app': m.group('app'),
+                'play_path': m.group('playpath'),
+                'player_path': 'http://tvnoviny.nova.cz/static/shared/app/videojs/video-js.swf',
+                'ext': 'flv',
+            }]
+        else:
+            formats = [{
+                'url': video_url,
+            }]
+        self._sort_formats(formats)
 
         title = mediafile.get('meta', {}).get('title') or self._og_search_title(webpage)
         description = clean_html(self._og_search_description(webpage, default=None))
         thumbnail = config.get('poster')
 
-        mobj = None
         if site == 'novaplus':
-            mobj = re.search(r'(?P<day>\d{1,2})-(?P<month>\d{1,2})-(?P<year>\d{4})$', display_id)
-        if site == 'fanda':
-            mobj = re.search(
-                r'<span class="date_time">(?P<day>\d{1,2})\.(?P<month>\d{1,2})\.(?P<year>\d{4})\b', webpage)
-        if mobj:
-            upload_date = '{}{:02d}{:02d}'.format(mobj.group('year'), int(mobj.group('month')), int(mobj.group('day')))
+            upload_date = unified_strdate(self._search_regex(
+                r'(\d{1,2}-\d{1,2}-\d{4})$', display_id, 'upload date', default=None))
+        elif site == 'fanda':
+            upload_date = unified_strdate(self._search_regex(
+                r'<span class="date_time">(\d{1,2}\.\d{1,2}\.\d{4})', webpage, 'upload date', default=None))
         else:
             upload_date = None
 
@@ -161,6 +175,5 @@ class NovaIE(InfoExtractor):
             'description': description,
             'upload_date': upload_date,
             'thumbnail': thumbnail,
-            'url': video_url,
-            'ext': ext,
+            'formats': formats,
         }