Merge pull request #601 from paullik/no-post-overwrites

[youtube-dl] / youtube_dl / InfoExtractors.py

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 6201ccad7c0ec2b26071bd3d6b7d6264fbd47bcb..697c031c5119176874558aef23eadb163e45fcdd 100755 (executable)
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -32,7 +32,7 @@ class InfoExtractor(object):
 
     id:             Video identifier.
     url:            Final video URL.
-    uploader:       Nickname of the video uploader, unescaped.
+    uploader:       Full name of the video uploader, unescaped.
     upload_date:    Video upload date (YYYYMMDD).
     title:          Video title, unescaped.
     ext:            Video filename extension.
@@ -42,6 +42,7 @@ class InfoExtractor(object):
     format:         The video format, defaults to ext (used for --get-format)
     thumbnail:      Full URL to a video thumbnail image.
     description:    One-line video description.
+    uploader_id:    Nickname or id of the video uploader.
     player_url:     SWF Player URL (used for rtmpdump).
     subtitles:      The .srt file contents.
     urlhandle:      [internal] The urlHandle to be used to download the file,
@@ -384,10 +385,18 @@ class YoutubeIE(InfoExtractor):
 
         # uploader
         if 'author' not in video_info:
-            self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+            self._downloader.trouble(u'ERROR: unable to extract uploader name')
             return
         video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0])
 
+        # uploader_id
+        video_uploader_id = None
+        mobj = re.search(r'<link itemprop="url" href="http://www.youtube.com/user/([^"]+)">', video_webpage)
+        if mobj is not None:
+            video_uploader_id = mobj.group(1)
+        else:
+            self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
+
         # title
         if 'title' not in video_info:
             self._downloader.trouble(u'ERROR: unable to extract video title')
@@ -495,6 +504,7 @@ class YoutubeIE(InfoExtractor):
                 'id':       video_id,
                 'url':      video_real_url,
                 'uploader': video_uploader,
+                'uploader_id': video_uploader_id,
                 'upload_date':  upload_date,
                 'title':    video_title,
                 'ext':      video_extension,
@@ -994,8 +1004,9 @@ class VimeoIE(InfoExtractor):
         # Extract title
         video_title = config["video"]["title"]
 
-        # Extract uploader
+        # Extract uploader and uploader_id
         video_uploader = config["video"]["owner"]["name"]
+        video_uploader_id = config["video"]["owner"]["url"].split('/')[-1]
 
         # Extract video thumbnail
         video_thumbnail = config["video"]["thumbnail"]
@@ -1007,9 +1018,9 @@ class VimeoIE(InfoExtractor):
 
         # Extract upload date
         video_upload_date = None
-        mobj = re.search(r'<span id="clip-date" style="display:none">[^:]*: (.*?)( \([^\(]*\))?</span>', webpage)
+        mobj = re.search(r'<meta itemprop="dateCreated" content="(\d{4})-(\d{2})-(\d{2})T', webpage)
         if mobj is not None:
-            video_upload_date = mobj.group(1)
+            video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3)
 
         # Vimeo specific: extract request signature and timestamp
         sig = config['request']['signature']
@@ -1047,6 +1058,7 @@ class VimeoIE(InfoExtractor):
             'id':       video_id,
             'url':      video_url,
             'uploader': video_uploader,
+            'uploader_id': video_uploader_id,
             'upload_date':  video_upload_date,
             'title':    video_title,
             'ext':      video_extension,
@@ -3632,3 +3644,52 @@ class JustinTVIE(InfoExtractor):
                 break
             offset += limit
         return info
+
+class FunnyOrDieIE(InfoExtractor):
+    _VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$'
+    IE_NAME = u'FunnyOrDie'
+
+    def report_extraction(self, video_id):
+        self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        if mobj is None:
+            self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+            return
+
+        video_id = mobj.group('id')
+        self.report_extraction(video_id)
+        try:
+            urlh = compat_urllib_request.urlopen(url)
+            webpage_bytes = urlh.read()
+            webpage = webpage_bytes.decode('utf-8', 'ignore')
+        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+            self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
+            return
+
+        m = re.search(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"', webpage, re.DOTALL)
+        if not m:
+            self._downloader.trouble(u'ERROR: unable to find video information')
+        video_url = unescapeHTML(m.group('url'))
+        print(video_url)
+
+        m = re.search(r"class='player_page_h1'>\s+<a.*?>(?P<title>.*?)</a>", webpage)
+        if not m:
+            self._downloader.trouble(u'Cannot find video title')
+        title = unescapeHTML(m.group('title'))
+
+        m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage)
+        if m:
+            desc = unescapeHTML(m.group('desc'))
+        else:
+            desc = None
+
+        info = {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': title,
+            'description': desc,
+        }
+        return [info]