[firedrive] Add new extractor. Addresses #3095

youtube_dl/extractor/__init__.py

@@ -83,6 +83,7 @@
 from .facebook import FacebookIE
 from .faz import FazIE
 from .fc2 import FC2IE
+from .firedrive import FiredriveIE
 from .firstpost import FirstpostIE
 from .firsttv import FirstTVIE
 from .fivemin import FiveMinIE

youtube_dl/extractor/firedrive.py

@@ -0,0 +1,81 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    compat_urllib_parse,
+    compat_urllib_request,
+    determine_ext,
+)
+
+
+class FiredriveIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?firedrive\.com/' + \
+                 '(?:file|embed)/(?P<id>[0-9a-zA-Z]+)'
+    _FILE_DELETED_REGEX = r'<div class="removed_file_image">'
+
+    _TESTS = [{
+        'url': 'https://www.firedrive.com/file/FEB892FA160EBD01',
+        'md5': 'd5d4252f80ebeab4dc2d5ceaed1b7970',
+        'info_dict': {
+            'id': 'FEB892FA160EBD01',
+            'ext': 'flv',
+            'title': 'bbb_theora_486kbit.flv',
+            'thumbnail': 're:http://.*\.jpg',
+        },
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        url = 'http://firedrive.com/file/%s' % video_id
+
+        webpage = self._download_webpage(url, video_id)
+
+        if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
+            raise ExtractorError(u'Video %s does not exist' % video_id,
+                                 expected=True)
+
+        fields = dict(re.findall(r'''(?x)<input\s+
+            type="hidden"\s+
+            name="([^"]+)"\s+
+            (?:id="[^"]+"\s+)?
+            value="([^"]*)"
+            ''', webpage))
+
+        post = compat_urllib_parse.urlencode(fields)
+        req = compat_urllib_request.Request(url, post)
+        req.add_header('Content-type', 'application/x-www-form-urlencoded')
+
+        # Apparently, this header is required for confirmation to work.
+        req.add_header('Host', 'www.firedrive.com')
+
+        webpage = self._download_webpage(req, video_id,
+                                         'Downloading video page')
+
+        title = self._search_regex(r'class="external_title_left">(.+)</div>',
+                                   webpage, 'title')
+        thumbnail = self._search_regex(r'image:\s?"(//[^\"]+)', webpage,
+                                       'thumbnail', fatal=False, default="")
+        url = self._search_regex(r'file:\s?\'(http[^\']+)\',',
+                                 webpage, 'file url')
+        ext = self._search_regex(r'type:\s?\'([^\']+)\',',
+                                 webpage, 'extension', fatal=False)
+
+        formats = [{
+            'format_id': 'sd',
+            'url': url,
+            'ext': ext or determine_ext(url),
+            'quality': 1,
+        }]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': "http:" + thumbnail,
+            'formats': formats,
+        }