aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2016-06-14 02:13:54 +0700
committerSergey M․ <dstftw@gmail.com>2016-06-14 02:13:54 +0700
commit1759672eede27be0a3d473c4b2925a0b10dce547 (patch)
tree38898949d53f5add6218ecdff322e6b91abe9941 /youtube_dl/extractor
parentfea55ef4a95d226668bd63742c4731832de93a79 (diff)
[wrzuta:playlist] Improve and simplify (Closes #9341)
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/extractors.py6
-rw-r--r--youtube_dl/extractor/wrzuta.py49
2 files changed, 27 insertions, 28 deletions
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 5a93fec6a..5fce9f47a 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -980,8 +980,10 @@ from .weiqitv import WeiqiTVIE
from .wimp import WimpIE
from .wistia import WistiaIE
from .worldstarhiphop import WorldStarHipHopIE
-from .wrzuta import WrzutaIE
-from .wrzuta import WrzutaPlaylistIE
+from .wrzuta import (
+ WrzutaIE,
+ WrzutaPlaylistIE,
+)
from .wsj import WSJIE
from .xbef import XBefIE
from .xboxclips import XboxClipsIE
diff --git a/youtube_dl/extractor/wrzuta.py b/youtube_dl/extractor/wrzuta.py
index 830649214..b811f57fb 100644
--- a/youtube_dl/extractor/wrzuta.py
+++ b/youtube_dl/extractor/wrzuta.py
@@ -7,6 +7,7 @@ from .common import InfoExtractor
from ..utils import (
int_or_none,
qualities,
+ remove_start,
)
@@ -82,10 +83,6 @@ class WrzutaIE(InfoExtractor):
}
-_ENTRY_PATTERN = r'<a href="(?P<playlist_entry_url>[^"]+)" target="_blank" class="playlist\-file\-page">'
-_PLAYLIST_SIZE_PATTERN = r'<div class="playlist-counter">[0-9]+/([0-9]+)</div>'
-
-
class WrzutaPlaylistIE(InfoExtractor):
"""
this class covers extraction of wrzuta playlist entries
@@ -101,10 +98,7 @@ class WrzutaPlaylistIE(InfoExtractor):
"""
IE_NAME = 'wrzuta.pl:playlist'
-
- _VALID_URL = r'https?://(?P<uploader>[0-9a-zA-Z]+)\.wrzuta\.pl/playlista/' \
- '(?P<id>[0-9a-zA-Z]+)/.*'
-
+ _VALID_URL = r'https?://(?P<uploader>[0-9a-zA-Z]+)\.wrzuta\.pl/playlista/(?P<id>[0-9a-zA-Z]+)'
_TESTS = [{
'url': 'http://miromak71.wrzuta.pl/playlista/7XfO4vE84iR/moja_muza',
'playlist_mincount': 14,
@@ -119,6 +113,9 @@ class WrzutaPlaylistIE(InfoExtractor):
'id': '6Nj3wQHx756',
'title': 'Lipiec - Lato 2015 Muzyka Świata',
},
+ }, {
+ 'url': 'http://miromak71.wrzuta.pl/playlista/7XfO4vE84iR',
+ 'only_matching': True,
}]
def _real_extract(self, url):
@@ -126,31 +123,31 @@ class WrzutaPlaylistIE(InfoExtractor):
playlist_id = mobj.group('id')
uploader = mobj.group('uploader')
- entries = []
-
webpage = self._download_webpage(url, playlist_id)
- playlist_size = self._html_search_regex(_PLAYLIST_SIZE_PATTERN, webpage, 'Size of the playlist')
- playlist_size = int(playlist_size) if playlist_size else 0
+ playlist_size = int_or_none(self._html_search_regex(
+ (r'<div[^>]+class=["\']playlist-counter["\'][^>]*>\d+/(\d+)',
+ r'<div[^>]+class=["\']all-counter["\'][^>]*>(.+?)</div>'),
+ webpage, 'playlist size', default=None))
- playlist_title = self._og_search_title(webpage).replace('Playlista: ', '', 1)
+ playlist_title = remove_start(
+ self._og_search_title(webpage), 'Playlista: ')
+ entries = []
if playlist_size:
- entries = list(map(
- lambda entry_url: self.url_result(entry_url),
- re.findall(_ENTRY_PATTERN, webpage)
- ))
-
+ entries = [
+ self.url_result(entry_url)
+ for _, entry_url in re.findall(
+ r'<a[^>]+href=(["\'])(http.+?)\1[^>]+class=["\']playlist-file-page',
+ webpage)]
if playlist_size > len(entries):
playlist_content = self._download_json(
- 'http://{uploader_id}.wrzuta.pl/xhr/get_playlist_offset/{playlist_id}'.format(
- uploader_id=uploader,
- playlist_id=playlist_id,
- ),
+ 'http://%s.wrzuta.pl/xhr/get_playlist_offset/%s' % (uploader, playlist_id),
playlist_id,
- 'Downloading playlist content as JSON metadata',
- 'Unable to download playlist content as JSON metadata',
- )
- entries += [self.url_result(entry['filelink']) for entry in playlist_content['files']]
+ 'Downloading playlist JSON',
+ 'Unable to download playlist JSON')
+ entries.extend([
+ self.url_result(entry['filelink'])
+ for entry in playlist_content.get('files', []) if entry.get('filelink')])
return self.playlist_result(entries, playlist_id, playlist_title)