aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl')
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/cliphunter.py59
2 files changed, 60 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 192baa9b8..1e8556124 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -27,6 +27,7 @@ from .cbs import CBSIE
from .channel9 import Channel9IE
from .cinemassacre import CinemassacreIE
from .clipfish import ClipfishIE
+from .cliphunter import CliphunterIE
from .clipsyndicate import ClipsyndicateIE
from .cmt import CMTIE
from .cnn import CNNIE
diff --git a/youtube_dl/extractor/cliphunter.py b/youtube_dl/extractor/cliphunter.py
new file mode 100644
index 000000000..d891fa301
--- /dev/null
+++ b/youtube_dl/extractor/cliphunter.py
@@ -0,0 +1,59 @@
+from __future__ import unicode_literals
+
+import re
+import string
+
+from .common import InfoExtractor
+from ..utils import (
+ ExtractorError,
+)
+
+translation_table = {
+ 'a': 'h', 'd': 'e', 'e': 'v', 'f': 'o', 'g': 'f', 'i': 'd', 'l': 'n',
+ 'm': 'a', 'n': 'm', 'p': 'u', 'q': 't', 'r': 's', 'v': 'p', 'x': 'r',
+ 'y': 'l', 'z': 'i',
+ '$': ':', '&': '.', '(': '=', '^': '&', '=': '/',
+}
+
+
+class CliphunterIE(InfoExtractor):
+ IE_NAME = 'cliphunter'
+
+ _VALID_URL = r'''(?x)http://(?:www\.)?cliphunter\.com/w/
+ (?P<id>[0-9]+)/
+ (?P<seo>.+?)(?:$|[#\?])
+ '''
+ _TEST = {
+ 'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
+ 'file': '1012420.flv',
+ 'md5': '15e7740f30428abf70f4223478dc1225',
+ 'info_dict': {
+ 'title': 'Fun Jynx Maze solo',
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ webpage = self._download_webpage(url, video_id)
+
+ pl_fiji = self._search_regex(
+ r'pl_fiji = \'([^\']+)\'', webpage, 'video data')
+ pl_c_qual = self._search_regex(
+ r'pl_c_qual = "(.)"', webpage, 'video quality')
+ video_title = self._search_regex(
+ r'mediaTitle = "([^"]+)"', webpage, 'title')
+
+ video_url = ''.join(translation_table.get(c, c) for c in pl_fiji)
+
+ formats = [{
+ 'url': video_url,
+ 'format_id': pl_c_qual,
+ }]
+
+ return {
+ 'id': video_id,
+ 'title': video_title,
+ 'formats': formats,
+ }