[viddler] Add basic support (Fixes #1520)

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index d1b7e5f991fa63664233670100a7ef54861c58c9..2b054e1c9498d1786f4652e6f7b72c07bdd0f0c8 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -117,6 +117,7 @@ from .veehd import VeeHDIE
 from .veoh import VeohIE
 from .vevo import VevoIE
 from .vice import ViceIE
 from .veoh import VeohIE
 from .vevo import VevoIE
 from .vice import ViceIE

+from .viddler import ViddlerIE

 from .videofyme import VideofyMeIE
 from .vimeo import VimeoIE, VimeoChannelIE
 from .vine import VineIE
 from .videofyme import VideofyMeIE
 from .vimeo import VimeoIE, VimeoChannelIE
 from .vine import VineIE

diff --git a/youtube_dl/extractor/viddler.py b/youtube_dl/extractor/viddler.py
new file mode 100644 (file)
index 0000000..12c84a9
--- /dev/null
+++ b/youtube_dl/extractor/viddler.py
@@ -0,0 +1,64 @@
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+)
+
+
+class ViddlerIE(InfoExtractor):
+    _VALID_URL = r'(?P<domain>https?://(?:www\.)?viddler.com)/(?:v|embed|player)/(?P<id>[0-9]+)'
+    _TEST = {
+        u"url": u"http://www.viddler.com/v/43903784",
+        u'file': u'43903784.mp4',
+        u'md5': u'fbbaedf7813e514eb7ca30410f439ac9',
+        u'info_dict': {
+            u"title": u"Video Made Easy",
+            u"uploader": u"viddler",
+            u"duration": 100.89,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        embed_url = mobj.group('domain') + u'/embed/' + video_id
+        webpage = self._download_webpage(embed_url, video_id)
+
+        video_sources_code = self._search_regex(
+            r"(?ms)sources\s*:\s*(\{.*?\})", webpage, u'video URLs')
+        video_sources = json.loads(video_sources_code.replace("'", '"'))
+
+        formats = [{
+            'url': video_url,
+            'format': format_id,
+        } for video_url, format_id in video_sources.items()]
+
+        title = self._html_search_regex(
+            r"title\s*:\s*'([^']*)'", webpage, u'title')
+        uploader = self._html_search_regex(
+            r"authorName\s*:\s*'([^']*)'", webpage, u'uploader', fatal=False)
+        duration_s = self._html_search_regex(
+            r"duration\s*:\s*([0-9.]*)", webpage, u'duration', fatal=False)
+        duration = float(duration_s) if duration_s else None
+        thumbnail = self._html_search_regex(
+            r"thumbnail\s*:\s*'([^']*)'",
+            webpage, u'thumbnail', fatal=False)
+
+        info = {
+            '_type': 'video',
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'duration': duration,
+            'formats': formats,
+        }
+
+        # TODO: Remove when #980 has been merged
+        info['formats'][-1]['ext'] = determine_ext(info['formats'][-1]['url'])
+        info.update(info['formats'][-1])
+
+        return info

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index f5f9cde99b0c65363a098923e4c350182896f7f1..e3feb12bfd05673d4c09797144afd4a14c0b6364 100644 (file)
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -175,7 +175,7 @@ def compat_ord(c):
 compiled_regex_type = type(re.compile(''))
 
 std_headers = {
 compiled_regex_type = type(re.compile(''))
 
 std_headers = {

-    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0',
+    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0 (Chrome)',

     'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
     'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
     'Accept-Encoding': 'gzip, deflate',
     'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
     'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
     'Accept-Encoding': 'gzip, deflate',