aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/__init__.py2
-rw-r--r--youtube_dl/extractor/archiveorg.py7
-rw-r--r--youtube_dl/extractor/dreisat.py6
-rw-r--r--youtube_dl/extractor/googleplus.py3
-rw-r--r--youtube_dl/extractor/mixcloud.py122
-rw-r--r--youtube_dl/extractor/soundcloud.py45
-rw-r--r--youtube_dl/extractor/subtitles.py5
-rw-r--r--youtube_dl/extractor/trilulilu.py4
-rw-r--r--youtube_dl/extractor/xhamster.py4
-rw-r--r--youtube_dl/extractor/youtube.py3
10 files changed, 99 insertions, 102 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 06f9542d2..19d57c2e9 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -82,7 +82,7 @@ from .sina import SinaIE
from .slashdot import SlashdotIE
from .slideshare import SlideshareIE
from .sohu import SohuIE
-from .soundcloud import SoundcloudIE, SoundcloudSetIE
+from .soundcloud import SoundcloudIE, SoundcloudSetIE, SoundcloudUserIE
from .spiegel import SpiegelIE
from .stanfordoc import StanfordOpenClassroomIE
from .statigram import StatigramIE
diff --git a/youtube_dl/extractor/archiveorg.py b/youtube_dl/extractor/archiveorg.py
index 7efd1d823..61ce4469a 100644
--- a/youtube_dl/extractor/archiveorg.py
+++ b/youtube_dl/extractor/archiveorg.py
@@ -46,6 +46,8 @@ class ArchiveOrgIE(InfoExtractor):
for fn,fdata in data['files'].items()
if 'Video' in fdata['format']]
formats.sort(key=lambda fdata: fdata['file_size'])
+ for f in formats:
+ f['ext'] = determine_ext(f['url'])
info = {
'_type': 'video',
@@ -61,7 +63,6 @@ class ArchiveOrgIE(InfoExtractor):
info['thumbnail'] = thumbnail
# TODO: Remove when #980 has been merged
- info['url'] = formats[-1]['url']
- info['ext'] = determine_ext(formats[-1]['url'])
+ info.update(formats[-1])
- return info \ No newline at end of file
+ return info
diff --git a/youtube_dl/extractor/dreisat.py b/youtube_dl/extractor/dreisat.py
index 64b465805..765cb1f37 100644
--- a/youtube_dl/extractor/dreisat.py
+++ b/youtube_dl/extractor/dreisat.py
@@ -54,6 +54,7 @@ class DreiSatIE(InfoExtractor):
'width': int(fe.find('./width').text),
'height': int(fe.find('./height').text),
'url': fe.find('./url').text,
+ 'ext': determine_ext(fe.find('./url').text),
'filesize': int(fe.find('./filesize').text),
'video_bitrate': int(fe.find('./videoBitrate').text),
'3sat_qualityname': fe.find('./quality').text,
@@ -79,7 +80,6 @@ class DreiSatIE(InfoExtractor):
}
# TODO: Remove when #980 has been merged
- info['url'] = formats[-1]['url']
- info['ext'] = determine_ext(formats[-1]['url'])
+ info.update(formats[-1])
- return info \ No newline at end of file
+ return info
diff --git a/youtube_dl/extractor/googleplus.py b/youtube_dl/extractor/googleplus.py
index f1cd88983..8895ad289 100644
--- a/youtube_dl/extractor/googleplus.py
+++ b/youtube_dl/extractor/googleplus.py
@@ -40,7 +40,8 @@ class GooglePlusIE(InfoExtractor):
self.report_extraction(video_id)
# Extract update date
- upload_date = self._html_search_regex('title="Timestamp">(.*?)</a>',
+ upload_date = self._html_search_regex(
+ ['title="Timestamp">(.*?)</a>', r'<a.+?class="g-M.+?>(.+?)</a>'],
webpage, u'upload date', fatal=False)
if upload_date:
# Convert timestring to a format suitable for filename
diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py
index 8245b5583..a200dcd74 100644
--- a/youtube_dl/extractor/mixcloud.py
+++ b/youtube_dl/extractor/mixcloud.py
@@ -5,34 +5,27 @@ import socket
from .common import InfoExtractor
from ..utils import (
compat_http_client,
- compat_str,
compat_urllib_error,
compat_urllib_request,
-
- ExtractorError,
+ unified_strdate,
)
class MixcloudIE(InfoExtractor):
- _WORKING = False # New API, but it seems good http://www.mixcloud.com/developers/documentation/
_VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
IE_NAME = u'mixcloud'
- def report_download_json(self, file_id):
- """Report JSON download."""
- self.to_screen(u'Downloading json')
-
- def get_urls(self, jsonData, fmt, bitrate='best'):
- """Get urls from 'audio_formats' section in json"""
- try:
- bitrate_list = jsonData[fmt]
- if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list:
- bitrate = max(bitrate_list) # select highest
-
- url_list = jsonData[fmt][bitrate]
- except TypeError: # we have no bitrate info.
- url_list = jsonData[fmt]
- return url_list
+ _TEST = {
+ u'url': u'http://www.mixcloud.com/dholbach/cryptkeeper/',
+ u'file': u'dholbach-cryptkeeper.mp3',
+ u'info_dict': {
+ u'title': u'Cryptkeeper',
+ u'description': u'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
+ u'uploader': u'Daniel Holbach',
+ u'uploader_id': u'dholbach',
+ u'upload_date': u'20111115',
+ },
+ }
def check_urls(self, url_list):
"""Returns 1st active url from list"""
@@ -45,71 +38,32 @@ class MixcloudIE(InfoExtractor):
return None
- def _print_formats(self, formats):
- print('Available formats:')
- for fmt in formats.keys():
- for b in formats[fmt]:
- try:
- ext = formats[fmt][b][0]
- print('%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1]))
- except TypeError: # we have no bitrate info
- ext = formats[fmt][0]
- print('%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1]))
- break
-
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
- # extract uploader & filename from url
- uploader = mobj.group(1).decode('utf-8')
- file_id = uploader + "-" + mobj.group(2).decode('utf-8')
-
- # construct API request
- file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json'
- # retrieve .json file with links to files
- request = compat_urllib_request.Request(file_url)
- try:
- self.report_download_json(file_url)
- jsonData = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- raise ExtractorError(u'Unable to retrieve file: %s' % compat_str(err))
-
- # parse JSON
- json_data = json.loads(jsonData)
- player_url = json_data['player_swf_url']
- formats = dict(json_data['audio_formats'])
-
- req_format = self._downloader.params.get('format', None)
-
- if self._downloader.params.get('listformats', None):
- self._print_formats(formats)
- return
-
- if req_format is None or req_format == 'best':
- for format_param in formats.keys():
- url_list = self.get_urls(formats, format_param)
- # check urls
- file_url = self.check_urls(url_list)
- if file_url is not None:
- break # got it!
- else:
- if req_format not in formats:
- raise ExtractorError(u'Format is not available')
-
- url_list = self.get_urls(formats, req_format)
- file_url = self.check_urls(url_list)
- format_param = req_format
- return [{
- 'id': file_id.decode('utf-8'),
- 'url': file_url.decode('utf-8'),
- 'uploader': uploader.decode('utf-8'),
- 'upload_date': None,
- 'title': json_data['name'],
- 'ext': file_url.split('.')[-1].decode('utf-8'),
- 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
- 'thumbnail': json_data['thumbnail_url'],
- 'description': json_data['description'],
- 'player_url': player_url.decode('utf-8'),
- }]
+ uploader = mobj.group(1)
+ cloudcast_name = mobj.group(2)
+ track_id = '-'.join((uploader, cloudcast_name))
+ api_url = 'http://api.mixcloud.com/%s/%s/' % (uploader, cloudcast_name)
+ webpage = self._download_webpage(url, track_id)
+ json_data = self._download_webpage(api_url, track_id,
+ u'Downloading cloudcast info')
+ info = json.loads(json_data)
+
+ preview_url = self._search_regex(r'data-preview-url="(.+?)"', webpage, u'preview url')
+ song_url = preview_url.replace('/previews/', '/cloudcasts/originals/')
+ template_url = re.sub(r'(stream\d*)', 'stream%d', song_url)
+ final_song_url = self.check_urls(template_url % i for i in range(30))
+
+ return {
+ 'id': track_id,
+ 'title': info['name'],
+ 'url': final_song_url,
+ 'ext': 'mp3',
+ 'description': info['description'],
+ 'thumbnail': info['pictures'].get('extra_large'),
+ 'uploader': info['user']['name'],
+ 'uploader_id': info['user']['username'],
+ 'upload_date': unified_strdate(info['created_time']),
+ 'view_count': info['play_count'],
+ }
diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py
index 5f3a5540d..29cd5617c 100644
--- a/youtube_dl/extractor/soundcloud.py
+++ b/youtube_dl/extractor/soundcloud.py
@@ -1,10 +1,12 @@
import json
import re
+import itertools
from .common import InfoExtractor
from ..utils import (
compat_str,
compat_urlparse,
+ compat_urllib_parse,
ExtractorError,
unified_strdate,
@@ -53,10 +55,11 @@ class SoundcloudIE(InfoExtractor):
def _resolv_url(cls, url):
return 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=' + cls._CLIENT_ID
- def _extract_info_dict(self, info, full_title=None):
+ def _extract_info_dict(self, info, full_title=None, quiet=False):
video_id = info['id']
name = full_title or video_id
- self.report_extraction(name)
+ if quiet == False:
+ self.report_extraction(name)
thumbnail = info['artwork_url']
if thumbnail is not None:
@@ -198,3 +201,41 @@ class SoundcloudSetIE(SoundcloudIE):
'id': info['id'],
'title': info['title'],
}
+
+
+class SoundcloudUserIE(SoundcloudIE):
+ _VALID_URL = r'https?://(www\.)?soundcloud.com/(?P<user>[^/]+)(/?(tracks/)?)?(\?.*)?$'
+ IE_NAME = u'soundcloud:user'
+
+ # it's in tests/test_playlists.py
+ _TEST = None
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ uploader = mobj.group('user')
+
+ url = 'http://soundcloud.com/%s/' % uploader
+ resolv_url = self._resolv_url(url)
+ user_json = self._download_webpage(resolv_url, uploader,
+ u'Downloading user info')
+ user = json.loads(user_json)
+
+ tracks = []
+ for i in itertools.count():
+ data = compat_urllib_parse.urlencode({'offset': i*50,
+ 'client_id': self._CLIENT_ID,
+ })
+ tracks_url = 'http://api.soundcloud.com/users/%s/tracks.json?' % user['id'] + data
+ response = self._download_webpage(tracks_url, uploader,
+ u'Downloading tracks page %s' % (i+1))
+ new_tracks = json.loads(response)
+ tracks.extend(self._extract_info_dict(track, quiet=True) for track in new_tracks)
+ if len(new_tracks) < 50:
+ break
+
+ return {
+ '_type': 'playlist',
+ 'id': compat_str(user['id']),
+ 'title': user['username'],
+ 'entries': tracks,
+ }
diff --git a/youtube_dl/extractor/subtitles.py b/youtube_dl/extractor/subtitles.py
index 97215f289..90de7de3a 100644
--- a/youtube_dl/extractor/subtitles.py
+++ b/youtube_dl/extractor/subtitles.py
@@ -10,8 +10,7 @@ class SubtitlesInfoExtractor(InfoExtractor):
@property
def _have_to_download_any_subtitles(self):
return any([self._downloader.params.get('writesubtitles', False),
- self._downloader.params.get('writeautomaticsub'),
- self._downloader.params.get('allsubtitles', False)])
+ self._downloader.params.get('writeautomaticsub')])
def _list_available_subtitles(self, video_id, webpage=None):
""" outputs the available subtitles for the video """
@@ -34,7 +33,7 @@ class SubtitlesInfoExtractor(InfoExtractor):
available_subs_list = {}
if self._downloader.params.get('writeautomaticsub', False):
available_subs_list.update(self._get_available_automatic_caption(video_id, video_webpage))
- if self._downloader.params.get('writesubtitles', False) or self._downloader.params.get('allsubtitles', False):
+ if self._downloader.params.get('writesubtitles', False):
available_subs_list.update(self._get_available_subtitles(video_id))
if not available_subs_list: # error, it didn't get the available subtitles
diff --git a/youtube_dl/extractor/trilulilu.py b/youtube_dl/extractor/trilulilu.py
index f278951ba..0bf028f61 100644
--- a/youtube_dl/extractor/trilulilu.py
+++ b/youtube_dl/extractor/trilulilu.py
@@ -52,6 +52,7 @@ class TriluliluIE(InfoExtractor):
{
'format': fnode.text,
'url': video_url_template % fnode.text,
+ 'ext': fnode.text.partition('-')[0]
}
for fnode in format_doc.findall('./formats/format')
@@ -67,7 +68,6 @@ class TriluliluIE(InfoExtractor):
}
# TODO: Remove when #980 has been merged
- info['url'] = formats[-1]['url']
- info['ext'] = formats[-1]['format'].partition('-')[0]
+ info.update(formats[-1])
return info
diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
index e50069586..fa759d30c 100644
--- a/youtube_dl/extractor/xhamster.py
+++ b/youtube_dl/extractor/xhamster.py
@@ -11,7 +11,7 @@ from ..utils import (
class XHamsterIE(InfoExtractor):
"""Information Extractor for xHamster"""
- _VALID_URL = r'(?:http://)?(?P<url>(?:www\.)?xhamster\.com/movies/(?P<id>[0-9]+)/.*\.html(?:\?.*)?)'
+ _VALID_URL = r'(?:http://)?(?:www.)?xhamster\.com/movies/(?P<id>[0-9]+)/.*\.html'
_TEST = {
u'url': u'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
u'file': u'1509445.flv',
@@ -27,7 +27,7 @@ class XHamsterIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
- mrss_url = 'http://' + mobj.group('url')
+ mrss_url = 'http://xhamster.com/movies/%s/.html?hd' % video_id
webpage = self._download_webpage(mrss_url, video_id)
mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index f49665925..e4a2e22bc 100644
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -139,7 +139,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
(
(?:https?://)? # http(s):// (optional)
(?:(?:(?:(?:\w+\.)?youtube(?:-nocookie)?\.com/|
- tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains
+ tube\.majestyc\.net/|
+ youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
(?:.*?\#/)? # handle anchor (#/) redirect urls
(?: # the various things that can precede the ID:
(?:(?:v|embed|e)/) # v/ or embed/ or e/
generated by cgit v1.2.3 (git 2.26.2) at 2024-08-20 03:34:03 +0000