etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 03:03:01 +00:00
Code Issues Projects Releases Wiki Activity

[aftonbladet] Modernize

Browse source
This commit is contained in:
Philipp Hagemeister 2014-03-10 10:27:40 +01:00
parent 5375d7ad84
commit fbc2dcb40b
1 changed files with 11 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

19
youtube_dl/extractor/aftonbladet.py
View file

@ -8,7 +8,7 @@
class AftonbladetIE(InfoExtractor): class AftonbladetIE(InfoExtractor):
_VALID_URL = r'^http://tv\.aftonbladet\.se/webbtv.+(?P<video_id>article\d+)\.ab$' _VALID_URL = r'^http://tv\.aftonbladet\.se/webbtv.+?(?P<video_id>article[0-9]+)\.ab(?:$|[?#])'
_TEST = { _TEST = {
'url': 'http://tv.aftonbladet.se/webbtv/nyheter/vetenskap/rymden/article36015.ab', 'url': 'http://tv.aftonbladet.se/webbtv/nyheter/vetenskap/rymden/article36015.ab',
'info_dict': { 'info_dict': {
@ -28,19 +28,21 @@ def _real_extract(self, url):
# find internal video meta data # find internal video meta data
META_URL = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json' META_URL = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json'
internal_meta_id = self._html_search_regex(r'data-aptomaId="([\w\d]+)"', webpage, 'internal_meta_id') internal_meta_id = self._html_search_regex(
r'data-aptomaId="([\w\d]+)"', webpage, 'internal_meta_id')
internal_meta_url = META_URL % internal_meta_id internal_meta_url = META_URL % internal_meta_id
internal_meta_json = self._download_json(internal_meta_url, video_id, 'Downloading video meta data') internal_meta_json = self._download_json(
internal_meta_url, video_id, 'Downloading video meta data')
# find internal video formats # find internal video formats
FORMATS_URL = 'http://aftonbladet-play.videodata.drvideo.aptoma.no/actions/video/?id=%s' FORMATS_URL = 'http://aftonbladet-play.videodata.drvideo.aptoma.no/actions/video/?id=%s'
internal_video_id = internal_meta_json['videoId'] internal_video_id = internal_meta_json['videoId']
internal_formats_url = FORMATS_URL % internal_video_id internal_formats_url = FORMATS_URL % internal_video_id
internal_formats_json = self._download_json(internal_formats_url, video_id, 'Downloading video formats') internal_formats_json = self._download_json(
internal_formats_url, video_id, 'Downloading video formats')
self.report_extraction(video_id)
formats = [] formats = []
for fmt in reversed(internal_formats_json['formats']['http']['pseudostreaming']['mp4']): for fmt in internal_formats_json['formats']['http']['pseudostreaming']['mp4']:
p = fmt['paths'][0] p = fmt['paths'][0]
formats.append({ formats.append({
'url': 'http://%s:%d/%s/%s' % (p['address'], p['port'], p['path'], p['filename']), 'url': 'http://%s:%d/%s/%s' % (p['address'], p['port'], p['path'], p['filename']),
@ -50,11 +52,12 @@ def _real_extract(self, url):
'tbr': fmt['bitrate'], 'tbr': fmt['bitrate'],
'protocol': 'http', 'protocol': 'http',
}) })
self._sort_formats(formats)
timestamp = datetime.datetime.fromtimestamp(internal_meta_json['timePublished']) timestamp = datetime.datetime.fromtimestamp(internal_meta_json['timePublished'])
upload_date = timestamp.strftime('%Y%m%d') upload_date = timestamp.strftime('%Y%m%d')
return [{ return {
'id': video_id, 'id': video_id,
'title': internal_meta_json['title'], 'title': internal_meta_json['title'],
'formats': formats, 'formats': formats,
@ -63,4 +66,4 @@ def _real_extract(self, url):
'upload_date': upload_date, 'upload_date': upload_date,
'duration': internal_meta_json['duration'], 'duration': internal_meta_json['duration'],
'view_count': internal_meta_json['views'], 'view_count': internal_meta_json['views'],
}] }