aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--AUTHORS1
-rwxr-xr-xyoutube_dl/YoutubeDL.py6
-rw-r--r--youtube_dl/extractor/generic.py24
-rw-r--r--youtube_dl/extractor/ivi.py27
-rw-r--r--youtube_dl/extractor/viddler.py63
5 files changed, 93 insertions, 28 deletions
diff --git a/AUTHORS b/AUTHORS
index 1596a7548..20e620c35 100644
--- a/AUTHORS
+++ b/AUTHORS
@@ -106,3 +106,4 @@ Johan K. Jensen
Yen Chi Hsuan
Enam Mijbah Noor
David Luhmer
+Shaya Goldberg
diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py
index b5dd77e3f..4c238c555 100755
--- a/youtube_dl/YoutubeDL.py
+++ b/youtube_dl/YoutubeDL.py
@@ -543,6 +543,11 @@ class YoutubeDL(object):
outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
tmpl = compat_expanduser(outtmpl)
filename = tmpl % template_dict
+ # Temporary fix for #4787
+ # 'Treat' all problem characters by passing filename through preferredencoding
+ # to workaround encoding issues with subprocess on python2 @ Windows
+ if sys.version_info < (3, 0) and sys.platform == 'win32':
+ filename = encodeFilename(filename, True).decode(preferredencoding())
return filename
except ValueError as err:
self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')')
@@ -1069,6 +1074,7 @@ class YoutubeDL(object):
selected_format = {
'requested_formats': formats_info,
'format': rf,
+ 'format_id': rf,
'ext': formats_info[0]['ext'],
'width': formats_info[0].get('width'),
'height': formats_info[0].get('height'),
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index ad16b8330..41884ed7a 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -498,6 +498,19 @@ class GenericIE(InfoExtractor):
'uploader': 'www.abc.net.au',
'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
}
+ },
+ # embedded viddler video
+ {
+ 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
+ 'info_dict': {
+ 'id': '4d03aad9',
+ 'ext': 'mp4',
+ 'uploader': 'deadspin',
+ 'title': 'WALL-TO-GORTAT',
+ 'timestamp': 1422285291,
+ 'upload_date': '20150126',
+ },
+ 'add_ie': ['Viddler'],
}
]
@@ -860,9 +873,16 @@ class GenericIE(InfoExtractor):
if mobj is not None:
return self.url_result(mobj.group('url'))
+ # Look for embedded Viddler player
+ mobj = re.search(
+ r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
+ webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'))
+
# Look for Ooyala videos
- mobj = (re.search(r'player.ooyala.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
- re.search(r'OO.Player.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage))
+ mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
+ re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage))
if mobj is not None:
return OoyalaIE._build_url_result(mobj.group('ec'))
diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py
index 7a400323d..e82594444 100644
--- a/youtube_dl/extractor/ivi.py
+++ b/youtube_dl/extractor/ivi.py
@@ -16,7 +16,7 @@ from ..utils import (
class IviIE(InfoExtractor):
IE_DESC = 'ivi.ru'
IE_NAME = 'ivi'
- _VALID_URL = r'https?://(?:www\.)?ivi\.ru/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<videoid>\d+)'
+ _VALID_URL = r'https?://(?:www\.)?ivi\.ru/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)'
_TESTS = [
# Single movie
@@ -63,29 +63,34 @@ class IviIE(InfoExtractor):
return int(m.group('commentcount')) if m is not None else 0
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('videoid')
+ video_id = self._match_id(url)
api_url = 'http://api.digitalaccess.ru/api/json/'
- data = {'method': 'da.content.get',
- 'params': [video_id, {'site': 's183',
- 'referrer': 'http://www.ivi.ru/watch/%s' % video_id,
- 'contentid': video_id
- }
- ]
+ data = {
+ 'method': 'da.content.get',
+ 'params': [
+ video_id, {
+ 'site': 's183',
+ 'referrer': 'http://www.ivi.ru/watch/%s' % video_id,
+ 'contentid': video_id
}
+ ]
+ }
request = compat_urllib_request.Request(api_url, json.dumps(data))
- video_json_page = self._download_webpage(request, video_id, 'Downloading video JSON')
+ video_json_page = self._download_webpage(
+ request, video_id, 'Downloading video JSON')
video_json = json.loads(video_json_page)
if 'error' in video_json:
error = video_json['error']
if error['origin'] == 'NoRedisValidData':
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
- raise ExtractorError('Unable to download video %s: %s' % (video_id, error['message']), expected=True)
+ raise ExtractorError(
+ 'Unable to download video %s: %s' % (video_id, error['message']),
+ expected=True)
result = video_json['result']
diff --git a/youtube_dl/extractor/viddler.py b/youtube_dl/extractor/viddler.py
index 0faa729c6..ef104dc29 100644
--- a/youtube_dl/extractor/viddler.py
+++ b/youtube_dl/extractor/viddler.py
@@ -5,27 +5,58 @@ from ..utils import (
float_or_none,
int_or_none,
)
+from ..compat import (
+ compat_urllib_request
+)
class ViddlerIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?viddler\.com/(?:v|embed|player)/(?P<id>[a-z0-9]+)'
- _TEST = {
- "url": "http://www.viddler.com/v/43903784",
+ _TESTS = [{
+ 'url': 'http://www.viddler.com/v/43903784',
'md5': 'ae43ad7cb59431ce043f0ff7fa13cbf4',
'info_dict': {
'id': '43903784',
'ext': 'mp4',
- "title": "Video Made Easy",
- 'description': 'You don\'t need to be a professional to make high-quality video content. Viddler provides some quick and easy tips on how to produce great video content with limited resources. ',
- "uploader": "viddler",
+ 'title': 'Video Made Easy',
+ 'description': 'md5:6a697ebd844ff3093bd2e82c37b409cd',
+ 'uploader': 'viddler',
'timestamp': 1335371429,
'upload_date': '20120425',
- "duration": 100.89,
+ 'duration': 100.89,
'thumbnail': 're:^https?://.*\.jpg$',
'view_count': int,
+ 'comment_count': int,
'categories': ['video content', 'high quality video', 'video made easy', 'how to produce video with limited resources', 'viddler'],
}
- }
+ }, {
+ 'url': 'http://www.viddler.com/v/4d03aad9/',
+ 'md5': 'faa71fbf70c0bee7ab93076fd007f4b0',
+ 'info_dict': {
+ 'id': '4d03aad9',
+ 'ext': 'mp4',
+ 'title': 'WALL-TO-GORTAT',
+ 'upload_date': '20150126',
+ 'uploader': 'deadspin',
+ 'timestamp': 1422285291,
+ 'view_count': int,
+ 'comment_count': int,
+ }
+ }, {
+ 'url': 'http://www.viddler.com/player/221ebbbd/0/',
+ 'md5': '0defa2bd0ea613d14a6e9bd1db6be326',
+ 'info_dict': {
+ 'id': '221ebbbd',
+ 'ext': 'mp4',
+ 'title': 'LETeens-Grammar-snack-third-conditional',
+ 'description': ' ',
+ 'upload_date': '20140929',
+ 'uploader': 'BCLETeens',
+ 'timestamp': 1411997190,
+ 'view_count': int,
+ 'comment_count': int,
+ }
+ }]
def _real_extract(self, url):
video_id = self._match_id(url)
@@ -33,14 +64,17 @@ class ViddlerIE(InfoExtractor):
json_url = (
'http://api.viddler.com/api/v2/viddler.videos.getPlaybackDetails.json?video_id=%s&key=v0vhrt7bg2xq1vyxhkct' %
video_id)
- data = self._download_json(json_url, video_id)['video']
+ headers = {'Referer': 'http://static.cdn-ec.viddler.com/js/arpeggio/v2/embed.html'}
+ request = compat_urllib_request.Request(json_url, None, headers)
+ data = self._download_json(request, video_id)['video']
formats = []
for filed in data['files']:
if filed.get('status', 'ready') != 'ready':
continue
+ format_id = filed.get('profile_id') or filed['profile_name']
f = {
- 'format_id': filed['profile_id'],
+ 'format_id': format_id,
'format_note': filed['profile_name'],
'url': self._proto_relative_url(filed['url']),
'width': int_or_none(filed.get('width')),
@@ -53,16 +87,15 @@ class ViddlerIE(InfoExtractor):
if filed.get('cdn_url'):
f = f.copy()
- f['url'] = self._proto_relative_url(filed['cdn_url'])
- f['format_id'] = filed['profile_id'] + '-cdn'
+ f['url'] = self._proto_relative_url(filed['cdn_url'], 'http:')
+ f['format_id'] = format_id + '-cdn'
f['source_preference'] = 1
formats.append(f)
if filed.get('html5_video_source'):
f = f.copy()
- f['url'] = self._proto_relative_url(
- filed['html5_video_source'])
- f['format_id'] = filed['profile_id'] + '-html5'
+ f['url'] = self._proto_relative_url(filed['html5_video_source'])
+ f['format_id'] = format_id + '-html5'
f['source_preference'] = 0
formats.append(f)
self._sort_formats(formats)
@@ -71,7 +104,6 @@ class ViddlerIE(InfoExtractor):
t.get('text') for t in data.get('tags', []) if 'text' in t]
return {
- '_type': 'video',
'id': video_id,
'title': data['title'],
'formats': formats,
@@ -81,5 +113,6 @@ class ViddlerIE(InfoExtractor):
'uploader': data.get('author'),
'duration': float_or_none(data.get('length')),
'view_count': int_or_none(data.get('view_count')),
+ 'comment_count': int_or_none(data.get('comment_count')),
'categories': categories,
}
generated by cgit v1.2.3 (git 2.26.2) at 2025-04-05 06:32:12 +0000