youtube-dl

commit: 07f7aad81c47a11483a357e53380fae1ffbadea9
parent 1e2575df8714ce9056e559058a187ec0ffd2d739
Author: Guillem Vela <guillemglez@gmail.com>
Date:   Thu, 27 Feb 2020 22:18:47 +0100

[ccma] improve metadata extraction(closes #27994)

- extract age_limit, alt_title, categories, series and episode_number
- fix timestamp multiple subtitles extraction

Diffstat:
M
youtube_dl/extractor/ccma.py
65
++++++++++++++++++++++++++++++++++++++++++++++++++++++-----------

1 file changed, 54 insertions(+), 11 deletions(-)
diff --git a/youtube_dl/extractor/ccma.py b/youtube_dl/extractor/ccma.py
@@ -1,6 +1,7 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import datetime
 import re
 
 from .common import InfoExtractor
@@ -8,8 +9,8 @@ from ..utils import (
     clean_html,
     int_or_none,
     parse_duration,
-    parse_iso8601,
     parse_resolution,
+    try_get,
     url_or_none,
 )
 
@@ -24,8 +25,9 @@ class CCMAIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'L\'espot de La Marató de TV3',
             'description': 'md5:f12987f320e2f6e988e9908e4fe97765',
-            'timestamp': 1470918540,
-            'upload_date': '20160811',
+            'timestamp': 1478608140,
+            'upload_date': '20161108',
+            'age_limit': 0,
         }
     }, {
         'url': 'http://www.ccma.cat/catradio/alacarta/programa/el-consell-de-savis-analitza-el-derbi/audio/943685/',
@@ -35,8 +37,24 @@ class CCMAIE(InfoExtractor):
             'ext': 'mp3',
             'title': 'El Consell de Savis analitza el derbi',
             'description': 'md5:e2a3648145f3241cb9c6b4b624033e53',
-            'upload_date': '20171205',
-            'timestamp': 1512507300,
+            'upload_date': '20170512',
+            'timestamp': 1494622500,
+            'vcodec': 'none',
+            'categories': ['Esports'],
+        }
+    }, {
+        'url': 'http://www.ccma.cat/tv3/alacarta/crims/crims-josep-tallada-lespereu-me-capitol-1/video/6031387/',
+        'md5': 'b43c3d3486f430f3032b5b160d80cbc3',
+        'info_dict': {
+            'id': '6031387',
+            'ext': 'mp4',
+            'title': 'Crims - Josep Talleda, l\'"Espereu-me" (capítol 1)',
+            'description': 'md5:7cbdafb640da9d0d2c0f62bad1e74e60',
+            'timestamp': 1582577700,
+            'upload_date': '20200224',
+            'subtitles': 'mincount:4',
+            'age_limit': 16,
+            'series': 'Crims',
         }
     }]
 
@@ -72,17 +90,27 @@ class CCMAIE(InfoExtractor):
 
         informacio = media['informacio']
         title = informacio['titol']
-        durada = informacio.get('durada', {})
+        durada = informacio.get('durada') or {}
         duration = int_or_none(durada.get('milisegons'), 1000) or parse_duration(durada.get('text'))
-        timestamp = parse_iso8601(informacio.get('data_emissio', {}).get('utc'))
+        tematica = try_get(informacio, lambda x: x['tematica']['text'])
+
+        timestamp = None
+        data_utc = try_get(informacio, lambda x: x['data_emissio']['utc'])
+        try:
+            timestamp = datetime.datetime.strptime(
+                data_utc, '%Y-%d-%mT%H:%M:%S%z').timestamp()
+        except TypeError:
+            pass
 
         subtitles = {}
-        subtitols = media.get('subtitols', {})
-        if subtitols:
-            sub_url = subtitols.get('url')
+        subtitols = media.get('subtitols') or []
+        if isinstance(subtitols, dict):
+            subtitols = [subtitols]
+        for st in subtitols:
+            sub_url = st.get('url')
             if sub_url:
                 subtitles.setdefault(
-                    subtitols.get('iso') or subtitols.get('text') or 'ca', []).append({
+                    st.get('iso') or st.get('text') or 'ca', []).append({
                         'url': sub_url,
                     })
 
@@ -97,6 +125,16 @@ class CCMAIE(InfoExtractor):
                     'height': int_or_none(imatges.get('alcada')),
                 }]
 
+        age_limit = None
+        codi_etic = try_get(informacio, lambda x: x['codi_etic']['id'])
+        if codi_etic:
+            codi_etic_s = codi_etic.split('_')
+            if len(codi_etic_s) == 2:
+                if codi_etic_s[1] == 'TP':
+                    age_limit = 0
+                else:
+                    age_limit = int_or_none(codi_etic_s[1])
+
         return {
             'id': media_id,
             'title': title,
@@ -106,4 +144,9 @@ class CCMAIE(InfoExtractor):
             'thumbnails': thumbnails,
             'subtitles': subtitles,
             'formats': formats,
+            'age_limit': age_limit,
+            'alt_title': informacio.get('titol_complet'),
+            'episode_number': int_or_none(informacio.get('capitol')),
+            'categories': [tematica] if tematica else None,
+            'series': informacio.get('programa'),
         }