commit 716889cab1b1cb38aa29d12251bfcac1039983a1
parent fcc3e6138b372e13578949dc724f456ae76dd065
Author: Sergey M․ <dstftw@gmail.com>
Date: Mon, 23 Feb 2015 21:30:46 +0600
Merge branch 'skypher-chirbit'
Diffstat:
3 files changed, 116 insertions(+), 1 deletion(-)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -63,6 +63,10 @@ from .ccc import CCCIE
from .ceskatelevize import CeskaTelevizeIE
from .channel9 import Channel9IE
from .chilloutzone import ChilloutzoneIE
+from .chirbit import (
+ ChirbitIE,
+ ChirbitProfileIE,
+)
from .cinchcast import CinchcastIE
from .clipfish import ClipfishIE
from .cliphunter import CliphunterIE
@@ -425,7 +429,10 @@ from .soundcloud import (
SoundcloudUserIE,
SoundcloudPlaylistIE
)
-from .soundgasm import SoundgasmIE
+from .soundgasm import (
+ SoundgasmIE,
+ SoundgasmProfileIE
+)
from .southpark import (
SouthParkIE,
SouthparkDeIE,
diff --git a/youtube_dl/extractor/chirbit.py b/youtube_dl/extractor/chirbit.py
@@ -0,0 +1,84 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+ parse_duration,
+ int_or_none,
+)
+
+
+class ChirbitIE(InfoExtractor):
+ IE_NAME = 'chirbit'
+ _VALID_URL = r'https?://(?:www\.)?chirb\.it/(?:(?:wp|pl)/|fb_chirbit_player\.swf\?key=)?(?P<id>[\da-zA-Z]+)'
+ _TESTS = [{
+ 'url': 'http://chirb.it/PrIPv5',
+ 'md5': '9847b0dad6ac3e074568bf2cfb197de8',
+ 'info_dict': {
+ 'id': 'PrIPv5',
+ 'ext': 'mp3',
+ 'title': 'Фасадстрой',
+ 'duration': 52,
+ 'view_count': int,
+ 'comment_count': int,
+ }
+ }, {
+ 'url': 'https://chirb.it/fb_chirbit_player.swf?key=PrIPv5',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ audio_id = self._match_id(url)
+
+ webpage = self._download_webpage(
+ 'http://chirb.it/%s' % audio_id, audio_id)
+
+ audio_url = self._search_regex(
+ r'"setFile"\s*,\s*"([^"]+)"', webpage, 'audio url')
+
+ title = self._search_regex(
+ r'itemprop="name">([^<]+)', webpage, 'title')
+ duration = parse_duration(self._html_search_meta(
+ 'duration', webpage, 'duration', fatal=False))
+ view_count = int_or_none(self._search_regex(
+ r'itemprop="playCount"\s*>(\d+)', webpage,
+ 'listen count', fatal=False))
+ comment_count = int_or_none(self._search_regex(
+ r'>(\d+) Comments?:', webpage,
+ 'comment count', fatal=False))
+
+ return {
+ 'id': audio_id,
+ 'url': audio_url,
+ 'title': title,
+ 'duration': duration,
+ 'view_count': view_count,
+ 'comment_count': comment_count,
+ }
+
+
+class ChirbitProfileIE(InfoExtractor):
+ IE_NAME = 'chirbit:profile'
+ _VALID_URL = r'https?://(?:www\.)?chirbit.com/(?:rss/)?(?P<id>[^/]+)'
+ _TEST = {
+ 'url': 'http://chirbit.com/ScarletBeauty',
+ 'info_dict': {
+ 'id': 'ScarletBeauty',
+ 'title': 'Chirbits by ScarletBeauty',
+ },
+ 'playlist_mincount': 3,
+ }
+
+ def _real_extract(self, url):
+ profile_id = self._match_id(url)
+
+ rss = self._download_xml(
+ 'http://chirbit.com/rss/%s' % profile_id, profile_id)
+
+ entries = [
+ self.url_result(audio_url.text, 'Chirbit')
+ for audio_url in rss.findall('./channel/item/link')]
+
+ title = rss.find('./channel/title').text
+
+ return self.playlist_result(entries, profile_id, title)
diff --git a/youtube_dl/extractor/soundgasm.py b/youtube_dl/extractor/soundgasm.py
@@ -4,9 +4,11 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
+from ..utils import clean_html
class SoundgasmIE(InfoExtractor):
+ IE_NAME = 'soundgasm'
_VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P<user>[0-9a-zA-Z_\-]+)/(?P<title>[0-9a-zA-Z_\-]+)'
_TEST = {
'url': 'http://soundgasm.net/u/ytdl/Piano-sample',
@@ -38,3 +40,25 @@ class SoundgasmIE(InfoExtractor):
'title': audio_title,
'description': description
}
+
+class SoundgasmProfileIE(InfoExtractor):
+ IE_NAME = 'soundgasm:profile'
+ _VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P<id>[^/]+)/?(?:\#.*)?$'
+ _TEST = {
+ 'url': 'http://soundgasm.net/u/ytdl',
+ 'info_dict': {
+ 'id': 'ytdl',
+ },
+ 'playlist_count': 1,
+ }
+
+ def _real_extract(self, url):
+ profile_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, profile_id)
+
+ entries = [
+ self.url_result(audio_url, 'Soundgasm')
+ for audio_url in re.findall(r'href="([^"]+/u/%s/[^"]+)' % profile_id, webpage)]
+
+ return self.playlist_result(entries, profile_id)
