youtube-dl

commit 136c8bd2757709fa18da3670e34435cb177b0905
parent 1bf5423e82d17ebaa496865cfcfa845b4257e13e
Author: Sergey M <dstftw@gmail.com>
Date:   Wed, 10 Sep 2014 19:04:14 +0700

Merge pull request #3709 from naglis/hostingbulk

[hostingbulk] Add new extractor
Diffstat:
M
youtube_dl/extractor/__init__.py
 | 
1
+
A
youtube_dl/extractor/hostingbulk.py
 | 
88
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

2 files changed, 89 insertions(+), 0 deletions(-)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -140,6 +140,7 @@ from .hark import HarkIE
 from .helsinki import HelsinkiIE
 from .hentaistigma import HentaiStigmaIE
 from .hornbunny import HornBunnyIE
+from .hostingbulk import HostingBulkIE
 from .hotnewhiphop import HotNewHipHopIE
 from .howcast import HowcastIE
 from .howstuffworks import HowStuffWorksIE
diff --git a/youtube_dl/extractor/hostingbulk.py b/youtube_dl/extractor/hostingbulk.py
@@ -0,0 +1,88 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    compat_urllib_request,
+    int_or_none,
+    urlencode_postdata,
+)
+
+
+class HostingBulkIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+        https?://(?:www\.)?hostingbulk\.com/
+        (?:embed-)?(?P<id>[A-Za-z0-9]{12})(?:-\d+x\d+)?\.html'''
+    _FILE_DELETED_REGEX = r'<b>File Not Found</b>'
+    _TEST = {
+        'url': 'http://hostingbulk.com/n0ulw1hv20fm.html',
+        'md5': '6c8653c8ecf7ebfa83b76e24b7b2fe3f',
+        'info_dict': {
+            'id': 'n0ulw1hv20fm',
+            'ext': 'mp4',
+            'title': 'md5:5afeba33f48ec87219c269e054afd622',
+            'filesize': 6816081,
+            'thumbnail': 're:^http://.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        url = 'http://hostingbulk.com/{0:}.html'.format(video_id)
+
+        # Custom request with cookie to set language to English, so our file
+        # deleted regex would work.
+        request = compat_urllib_request.Request(
+            url, headers={'Cookie': 'lang=english'})
+        webpage = self._download_webpage(request, video_id)
+
+        if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
+            raise ExtractorError('Video %s does not exist' % video_id,
+                                 expected=True)
+
+        title = self._html_search_regex(r'<h3>(.*?)</h3>', webpage, 'title')
+        filesize = int_or_none(
+            self._search_regex(
+                r'<small>\((\d+)\sbytes?\)</small>',
+                webpage,
+                'filesize',
+                fatal=False
+            )
+        )
+        thumbnail = self._search_regex(
+            r'<img src="([^"]+)".+?class="pic"',
+            webpage, 'thumbnail', fatal=False)
+        rand = self._search_regex(
+            r'<input.+?name="rand" value="([^"]+)">', webpage, 'rand')
+
+        fields = {
+            'id': video_id,
+            'method_free': '',
+            'method_premium': '',
+            'op': 'download2',
+            'rand': rand,
+            'referer': '',
+        }
+        request = compat_urllib_request.Request(url, urlencode_postdata(fields))
+        request.add_header('Content-type', 'application/x-www-form-urlencoded')
+        response = self._request_webpage(request, video_id,
+                                         'Submiting download request')
+        video_url = response.geturl()
+
+        formats = [{
+            'format_id': 'sd',
+            'filesize': filesize,
+            'url': video_url,
+        }]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }