[Rte] Improve extractor

This commit is contained in:
dinesh 2014-10-27 01:08:51 +05:30
parent 25fadd06d0
commit 0551a02b82

View File

@ -18,7 +18,7 @@ class RteIE(InfoExtractor):
'title': 'Nine News',
'thumbnail': 're:^https?://.*\.jpg$',
'description': 'The One O\'Clock News followed by Weather.',
'duration': 1622963.0,
'duration': 1622.963,
}
}
@ -29,7 +29,7 @@ def _real_extract(self, url):
title = self._og_search_title(webpage)
description = self._search_regex(r'<meta name="description" content="(.*?)" />', webpage, 'description')
duration = float_or_none(self._html_search_meta('duration', webpage, 'duration'))
duration = float_or_none(self._html_search_meta('duration', webpage, 'duration'), 1000)
thumbnail_id = self._search_regex(r'<meta name="thumbnail" content="uri:irus:(.*?)" />', webpage, 'thumbnail')
thumbnail = 'http://img.rasset.ie/' + thumbnail_id + '.jpg'
@ -40,8 +40,13 @@ def _real_extract(self, url):
# f4m_url = server + relative_url
f4m_url = json_string['shows'][0]['media:group'][0]['rte:server'] + json_string['shows'][0]['media:group'][0]['url']
f4m_formats = self._extract_f4m_formats(f4m_url, video_id)
for f in f4m_formats:
del f['tbr']
f4m_formats = [{
'format_id': f['format_id'],
'url': f['url'],
'ext': 'mp4',
'width': f['width'],
'height': f['height'],
} for f in f4m_formats ]
return {
'id': video_id,