Browse Source

[revison3] fix video_id for --download-archive

totalwebcasting
remitamine 9 years ago
parent
commit
2629a3802c
1 changed files with 14 additions and 6 deletions
  1. +14
    -6
      youtube_dl/extractor/revision3.py

+ 14
- 6
youtube_dl/extractor/revision3.py View File

@ -19,7 +19,7 @@ class Revision3IE(InfoExtractor):
'url': 'http://www.revision3.com/technobuffalo/5-google-predictions-for-2016', 'url': 'http://www.revision3.com/technobuffalo/5-google-predictions-for-2016',
'md5': 'd94a72d85d0a829766de4deb8daaf7df', 'md5': 'd94a72d85d0a829766de4deb8daaf7df',
'info_dict': { 'info_dict': {
'id': '73034',
'id': '71089',
'display_id': 'technobuffalo/5-google-predictions-for-2016', 'display_id': 'technobuffalo/5-google-predictions-for-2016',
'ext': 'webm', 'ext': 'webm',
'title': '5 Google Predictions for 2016', 'title': '5 Google Predictions for 2016',
@ -42,7 +42,7 @@ class Revision3IE(InfoExtractor):
}, { }, {
'url': 'https://testtube.com/dnews/5-weird-ways-plants-can-eat-animals?utm_source=FB&utm_medium=DNews&utm_campaign=DNewsSocial', 'url': 'https://testtube.com/dnews/5-weird-ways-plants-can-eat-animals?utm_source=FB&utm_medium=DNews&utm_campaign=DNewsSocial',
'info_dict': { 'info_dict': {
'id': '60163',
'id': '58227',
'display_id': 'dnews/5-weird-ways-plants-can-eat-animals', 'display_id': 'dnews/5-weird-ways-plants-can-eat-animals',
'duration': 275, 'duration': 275,
'ext': 'webm', 'ext': 'webm',
@ -56,7 +56,7 @@ class Revision3IE(InfoExtractor):
}, { }, {
'url': 'http://testtube.com/tt-editors-picks/the-israel-palestine-conflict-explained-in-ten-min', 'url': 'http://testtube.com/tt-editors-picks/the-israel-palestine-conflict-explained-in-ten-min',
'info_dict': { 'info_dict': {
'id': '73573',
'id': '71618',
'ext': 'mp4', 'ext': 'mp4',
'display_id': 'tt-editors-picks/the-israel-palestine-conflict-explained-in-ten-min', 'display_id': 'tt-editors-picks/the-israel-palestine-conflict-explained-in-ten-min',
'title': 'The Israel-Palestine Conflict Explained in Ten Minutes', 'title': 'The Israel-Palestine Conflict Explained in Ten Minutes',
@ -81,6 +81,7 @@ class Revision3IE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
domain, display_id = re.match(self._VALID_URL, url).groups() domain, display_id = re.match(self._VALID_URL, url).groups()
site = domain.split('.')[0]
page_info = self._download_json( page_info = self._download_json(
self._PAGE_DATA_TEMPLATE % (domain, display_id, domain), display_id) self._PAGE_DATA_TEMPLATE % (domain, display_id, domain), display_id)
@ -88,6 +89,7 @@ class Revision3IE(InfoExtractor):
page_type = page_data['type'] page_type = page_data['type']
if page_type in ('episode', 'embed'): if page_type in ('episode', 'embed'):
show_data = page_data['show']['data'] show_data = page_data['show']['data']
page_id = compat_str(page_data['id'])
video_id = compat_str(page_data['video']['data']['id']) video_id = compat_str(page_data['video']['data']['id'])
preference = qualities(['mini', 'small', 'medium', 'large']) preference = qualities(['mini', 'small', 'medium', 'large'])
@ -98,7 +100,7 @@ class Revision3IE(InfoExtractor):
} for image_id, image_url in page_data.get('images', {}).items()] } for image_id, image_url in page_data.get('images', {}).items()]
info = { info = {
'id': video_id,
'id': page_id,
'display_id': display_id, 'display_id': display_id,
'title': unescapeHTML(page_data['name']), 'title': unescapeHTML(page_data['name']),
'description': unescapeHTML(page_data.get('summary')), 'description': unescapeHTML(page_data.get('summary')),
@ -107,6 +109,7 @@ class Revision3IE(InfoExtractor):
'uploader': show_data.get('name'), 'uploader': show_data.get('name'),
'uploader_id': show_data.get('slug'), 'uploader_id': show_data.get('slug'),
'thumbnails': thumbnails, 'thumbnails': thumbnails,
'extractor_key': site,
} }
if page_type == 'embed': if page_type == 'embed':
@ -153,8 +156,13 @@ class Revision3IE(InfoExtractor):
entries = [] entries = []
page_num = 1 page_num = 1
while True: while True:
entries.extend([self.url_result(
'http://%s%s' % (domain, episode['path'])) for episode in episodes_data])
entries.extend([{
'_type': 'url',
'url': 'http://%s%s' % (domain, episode['path']),
'id': compat_str(episode['id']),
'ie_key': 'Revision3',
'extractor_key': site,
} for episode in episodes_data])
processed_episodes += len(episodes_data) processed_episodes += len(episodes_data)
if processed_episodes == num_episodes: if processed_episodes == num_episodes:
break break


Loading…
Cancel
Save