X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fjamendo.py;h=c218276184ab4acf9086404cdb679a74e24f353b;hb=77d95677b7ab4a9840ef142b14627b07a9a31120;hp=4aacd10f4482df11eb383b73932be321742d84d0;hpb=b17422753fbaf4e973c42a4dee7b4a071bd9a692;p=youtube-dl
diff --git a/youtube_dl/extractor/jamendo.py b/youtube_dl/extractor/jamendo.py
index 4aacd10f4..c21827618 100644
--- a/youtube_dl/extractor/jamendo.py
+++ b/youtube_dl/extractor/jamendo.py
@@ -2,116 +2,149 @@
from __future__ import unicode_literals
import re
-from collections import namedtuple
from ..compat import compat_urlparse
from .common import InfoExtractor
+from ..utils import parse_duration
-FormatData = namedtuple('FormatData', [
- 'format_id', 'sub_domain', 'ext', 'quality'])
+class JamendoBaseIE(InfoExtractor):
+ def _extract_meta(self, webpage, fatal=True):
+ title = self._og_search_title(
+ webpage, default=None) or self._search_regex(
+ r'
([^<]+)', webpage,
+ 'title', default=None)
+ if title:
+ title = self._search_regex(
+ r'(.+?)\s*\|\s*Jamendo Music', title, 'title', default=None)
+ if not title:
+ title = self._html_search_meta(
+ 'name', webpage, 'title', fatal=fatal)
+ mobj = re.search(r'(.+) - (.+)', title or '')
+ artist, second = mobj.groups() if mobj else [None] * 2
+ return title, artist, second
-class JamendoIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?jamendo\.com/track/(?P[0-9]+)/(?P[\w-]+)'
- _TEST = {
+
+class JamendoIE(JamendoBaseIE):
+ _VALID_URL = r'''(?x)
+ https?://
+ (?:
+ licensing\.jamendo\.com/[^/]+|
+ (?:www\.)?jamendo\.com
+ )
+ /track/(?P[0-9]+)/(?P[^/?#&]+)
+ '''
+ _TESTS = [{
'url': 'https://www.jamendo.com/track/196219/stories-from-emona-i',
'md5': '6e9e82ed6db98678f171c25a8ed09ffd',
'info_dict': {
'id': '196219',
'display_id': 'stories-from-emona-i',
'ext': 'flac',
- 'title': 'Stories from Emona I',
- 'thumbnail': 're:^https?://.*\.jpg'
+ 'title': 'Maya FilipiÄ - Stories from Emona I',
+ 'artist': 'Maya FilipiÄ',
+ 'track': 'Stories from Emona I',
+ 'duration': 210,
+ 'thumbnail': r're:^https?://.*\.jpg'
}
- }
+ }, {
+ 'url': 'https://licensing.jamendo.com/en/track/1496667/energetic-rock',
+ 'only_matching': True,
+ }]
def _real_extract(self, url):
- url_data = self._VALID_URL_RE.match(url)
- track_id = url_data.group('id')
- display_id = url_data.group('display_id')
- webpage = self._download_webpage(url, display_id)
+ mobj = self._VALID_URL_RE.match(url)
+ track_id = mobj.group('id')
+ display_id = mobj.group('display_id')
+
+ webpage = self._download_webpage(
+ 'https://www.jamendo.com/track/%s/%s' % (track_id, display_id),
+ display_id)
+
+ title, artist, track = self._extract_meta(webpage)
+
+ formats = [{
+ 'url': 'https://%s.jamendo.com/?trackid=%s&format=%s&from=app-97dab294'
+ % (sub_domain, track_id, format_id),
+ 'format_id': format_id,
+ 'ext': ext,
+ 'quality': quality,
+ } for quality, (format_id, sub_domain, ext) in enumerate((
+ ('mp31', 'mp3l', 'mp3'),
+ ('mp32', 'mp3d', 'mp3'),
+ ('ogg1', 'ogg', 'ogg'),
+ ('flac', 'flac', 'flac'),
+ ))]
+ self._sort_formats(formats)
thumbnail = self._html_search_meta(
'image', webpage, 'thumbnail', fatal=False)
- title = self._html_search_meta('name', webpage, 'title')
-
- url_template = 'https://%s.jamendo.com/?trackid=%s&format=%s&from=app-97dab294'
- format_data = [
- FormatData(
- format_id='mp31', sub_domain='mp3l', ext='mp3', quality=0),
- FormatData(
- format_id='mp32', sub_domain='mp3d', ext='mp3', quality=1),
- FormatData(
- format_id='ogg1', sub_domain='ogg', ext='ogg', quality=2),
- FormatData(
- format_id='flac', sub_domain='flac', ext='flac', quality=3),
- ]
- formats = [
- {
- 'format_id': fd.format_id,
- 'url': url_template % (fd.sub_domain, track_id, fd.format_id),
- 'ext': fd.ext,
- 'quality': fd.quality
- }
- for fd in format_data
- ]
- self._check_formats(formats, video_id=display_id)
+ duration = parse_duration(self._search_regex(
+ r']+itemprop=["\']duration["\'][^>]+content=["\'](.+?)["\']',
+ webpage, 'duration', fatal=False))
+
return {
'id': track_id,
'display_id': display_id,
'thumbnail': thumbnail,
'title': title,
+ 'duration': duration,
+ 'artist': artist,
+ 'track': track,
'formats': formats
}
-class JamendoAlbumIE(InfoExtractor):
+class JamendoAlbumIE(JamendoBaseIE):
_VALID_URL = r'https?://(?:www\.)?jamendo\.com/album/(?P[0-9]+)/(?P[\w-]+)'
_TEST = {
'url': 'https://www.jamendo.com/album/121486/duck-on-cover',
'info_dict': {
'id': '121486',
- 'title': 'Duck On Cover'
+ 'title': 'Shearer - Duck On Cover'
},
- 'playlist_mincount': 2,
- 'playlist': [
- {
- 'md5': 'e1a2fcb42bda30dfac990212924149a8',
- 'info_dict': {
- 'id': '1032333',
- 'ext': 'flac',
- 'title': 'Warmachine'
- }
- },
- {
- 'md5': '1f358d7b2f98edfe90fd55dac0799d50',
- 'info_dict': {
- 'id': '1032330',
- 'ext': 'flac',
- 'title': 'Without Your Ghost'
- }
+ 'playlist': [{
+ 'md5': 'e1a2fcb42bda30dfac990212924149a8',
+ 'info_dict': {
+ 'id': '1032333',
+ 'ext': 'flac',
+ 'title': 'Shearer - Warmachine',
+ 'artist': 'Shearer',
+ 'track': 'Warmachine',
+ }
+ }, {
+ 'md5': '1f358d7b2f98edfe90fd55dac0799d50',
+ 'info_dict': {
+ 'id': '1032330',
+ 'ext': 'flac',
+ 'title': 'Shearer - Without Your Ghost',
+ 'artist': 'Shearer',
+ 'track': 'Without Your Ghost',
}
- ],
+ }],
'params': {
'playlistend': 2
}
}
def _real_extract(self, url):
- url_data = self._VALID_URL_RE.match(url)
- album_id = url_data.group('id')
- webpage = self._download_webpage(url, url_data.group('display_id'))
+ mobj = self._VALID_URL_RE.match(url)
+ album_id = mobj.group('id')
- title = self._html_search_meta('name', webpage, 'title')
+ webpage = self._download_webpage(url, mobj.group('display_id'))
- track_paths = re.findall(r'', webpage)
- entries = [
- self.url_result(compat_urlparse.urljoin(url, path), ie=JamendoIE.ie_key())
- for path in track_paths
- ]
- return {
- '_type': 'playlist',
- 'id': album_id,
- 'title': title,
- 'entries': entries
- }
+ title, artist, album = self._extract_meta(webpage, fatal=False)
+
+ entries = [{
+ '_type': 'url_transparent',
+ 'url': compat_urlparse.urljoin(url, m.group('path')),
+ 'ie_key': JamendoIE.ie_key(),
+ 'id': self._search_regex(
+ r'/track/(\d+)', m.group('path'), 'track id', default=None),
+ 'artist': artist,
+ 'album': album,
+ } for m in re.finditer(
+ r']+href=(["\'])(?P(?:(?!\1).)+)\1[^>]+class=["\'][^>]*js-trackrow-albumpage-link',
+ webpage)]
+
+ return self.playlist_result(entries, album_id, title)