[ccma] improve metadata extraction(closes #27994)

- extract age_limit, alt_title, categories, series and episode_number
- fix timestamp multiple subtitles extraction
This commit is contained in:
Guillem Vela 2020-02-27 22:18:47 +01:00 committed by Remita Amine
parent 1e2575df87
commit 07f7aad81c

View File

@ -1,6 +1,7 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import datetime
import re import re
from .common import InfoExtractor from .common import InfoExtractor
@ -8,8 +9,8 @@ from ..utils import (
clean_html, clean_html,
int_or_none, int_or_none,
parse_duration, parse_duration,
parse_iso8601,
parse_resolution, parse_resolution,
try_get,
url_or_none, url_or_none,
) )
@ -24,8 +25,9 @@ class CCMAIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': 'L\'espot de La Marató de TV3', 'title': 'L\'espot de La Marató de TV3',
'description': 'md5:f12987f320e2f6e988e9908e4fe97765', 'description': 'md5:f12987f320e2f6e988e9908e4fe97765',
'timestamp': 1470918540, 'timestamp': 1478608140,
'upload_date': '20160811', 'upload_date': '20161108',
'age_limit': 0,
} }
}, { }, {
'url': 'http://www.ccma.cat/catradio/alacarta/programa/el-consell-de-savis-analitza-el-derbi/audio/943685/', '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', 'ext': 'mp3',
'title': 'El Consell de Savis analitza el derbi', 'title': 'El Consell de Savis analitza el derbi',
'description': 'md5:e2a3648145f3241cb9c6b4b624033e53', 'description': 'md5:e2a3648145f3241cb9c6b4b624033e53',
'upload_date': '20171205', 'upload_date': '20170512',
'timestamp': 1512507300, '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'] informacio = media['informacio']
title = informacio['titol'] 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')) 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 = {} subtitles = {}
subtitols = media.get('subtitols', {}) subtitols = media.get('subtitols') or []
if subtitols: if isinstance(subtitols, dict):
sub_url = subtitols.get('url') subtitols = [subtitols]
for st in subtitols:
sub_url = st.get('url')
if sub_url: if sub_url:
subtitles.setdefault( 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, 'url': sub_url,
}) })
@ -97,6 +125,16 @@ class CCMAIE(InfoExtractor):
'height': int_or_none(imatges.get('alcada')), '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 { return {
'id': media_id, 'id': media_id,
'title': title, 'title': title,
@ -106,4 +144,9 @@ class CCMAIE(InfoExtractor):
'thumbnails': thumbnails, 'thumbnails': thumbnails,
'subtitles': subtitles, 'subtitles': subtitles,
'formats': formats, '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'),
} }