youtube-dl

commit a8ae232fa9c24534bd9c838c793f182e6796fe4e
parent b9a324c0daafb9484a2575783b6b120a7de885ff
Author: remitamine <remitamine@gmail.com>
Date:   Mon, 21 Dec 2015 03:15:19 +0100

Merge branch 'googledrive' of github.com:remitamine/youtube-dl into remitamine-googledrive

Diffstat:
M
youtube_dl/extractor/__init__.py
 | 
1
+
M
youtube_dl/extractor/generic.py
 | 
6
++++++
A
youtube_dl/extractor/googledrive.py
 | 
88
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

3 files changed, 95 insertions(+), 0 deletions(-)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -231,6 +231,7 @@ from .globo import (
 from .godtube import GodTubeIE
 from .goldenmoustache import GoldenMoustacheIE
 from .golem import GolemIE
+from .googledrive import GoogleDriveIE
 from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
 from .goshgay import GoshgayIE
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
@@ -55,6 +55,7 @@ from .snagfilms import SnagFilmsEmbedIE
 from .screenwavemedia import ScreenwaveMediaIE
 from .mtv import MTVServicesEmbeddedIE
 from .pladform import PladformIE
+from .googledrive import GoogleDriveIE
 
 
 class GenericIE(InfoExtractor):
@@ -1769,6 +1770,11 @@ class GenericIE(InfoExtractor):
         if nbc_sports_url:
             return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
 
+        # Look for Google Drive embeds
+        google_drive_url = GoogleDriveIE._extract_url(webpage)
+        if google_drive_url:
+            return self.url_result(google_drive_url, 'GoogleDrive')
+
         # Look for UDN embeds
         mobj = re.search(
             r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
diff --git a/youtube_dl/extractor/googledrive.py b/youtube_dl/extractor/googledrive.py
@@ -0,0 +1,88 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+)
+
+
+class GoogleDriveIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28})'
+    _TEST = {
+        'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1',
+        'md5': '881f7700aec4f538571fa1e0eed4a7b6',
+        'info_dict': {
+            'id': '0ByeS4oOUV-49Zzh4R1J6R09zazQ',
+            'ext': 'mp4',
+            'title': 'Big Buck Bunny.mp4',
+            'duration': 46,
+        }
+    }
+    _FORMATS_EXT = {
+        '5': 'flv',
+        '6': 'flv',
+        '13': '3gp',
+        '17': '3gp',
+        '18': 'mp4',
+        '22': 'mp4',
+        '34': 'flv',
+        '35': 'flv',
+        '36': '3gp',
+        '37': 'mp4',
+        '38': 'mp4',
+        '43': 'webm',
+        '44': 'webm',
+        '45': 'webm',
+        '46': 'webm',
+        '59': 'mp4',
+    }
+
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28})',
+            webpage)
+        if mobj:
+            return 'https://drive.google.com/file/d/%s' % mobj.group('id')
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(
+            'http://docs.google.com/file/d/%s' % video_id, video_id, encoding='unicode_escape')
+
+        reason = self._search_regex(r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None)
+        if reason:
+            raise ExtractorError(reason)
+
+        title = self._search_regex(r'"title"\s*,\s*"([^"]+)', webpage, 'title')
+        duration = int_or_none(self._search_regex(
+            r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds', default=None))
+        fmt_stream_map = self._search_regex(
+            r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage, 'fmt stream map').split(',')
+        fmt_list = self._search_regex(r'"fmt_list"\s*,\s*"([^"]+)', webpage, 'fmt_list').split(',')
+
+        formats = []
+        for fmt, fmt_stream in zip(fmt_list, fmt_stream_map):
+            fmt_id, fmt_url = fmt_stream.split('|')
+            resolution = fmt.split('/')[1]
+            width, height = resolution.split('x')
+            formats.append({
+                'url': fmt_url,
+                'format_id': fmt_id,
+                'resolution': resolution,
+                'width': int_or_none(width),
+                'height': int_or_none(height),
+                'ext': self._FORMATS_EXT[fmt_id],
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'duration': duration,
+            'formats': formats,
+        }