[googledrive] Modernize

[youtube-dl] / youtube_dl / extractor / googledrive.py

diff --git a/youtube_dl/extractor/googledrive.py b/youtube_dl/extractor/googledrive.py
index e3d5c341892b25b97d42d520db5a154977cc9868..f354c9c7aa3f43a1aed6c04afb60fe5a9d8c434b 100644 (file)
--- a/youtube_dl/extractor/googledrive.py
+++ b/youtube_dl/extractor/googledrive.py
@@ -1,106 +1,88 @@
+from __future__ import unicode_literals
+
+import re
+
 from .common import InfoExtractor
-from ..utils import RegexNotFoundError
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+)
+
 
 class GoogleDriveIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://)?(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/))(?P<id>.+?)(?:&|/|$)'
+    _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 = {
-        '5': {'ext': 'flv'},
-        '6': {'ext': 'flv'},
-        '13': {'ext': '3gp'},
-        '17': {'ext': '3gp'},
-        '18': {'ext': 'mp4'},
-        '22': {'ext': 'mp4'},
-        '34': {'ext': 'flv'},
-        '35': {'ext': 'flv'},
-        '36': {'ext': '3gp'},
-        '37': {'ext': 'mp4'},
-        '38': {'ext': 'mp4'},
-        '43': {'ext': 'webm'},
-        '44': {'ext': 'webm'},
-        '45': {'ext': 'webm'},
-        '46': {'ext': 'webm'},
-        '59': {'ext': 'mp4'}
+    _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/'+video_id, video_id, encoding='unicode_escape'
-        )
-        try:
-            title = self._html_search_regex(
-                r'"title","(?P<title>.*?)"',
-                webpage,
-                'title',
-                group='title'
-            )
-            fmt_stream_map = self._html_search_regex(
-                r'"fmt_stream_map","(?P<fmt_stream_map>.*?)"',
-                webpage,
-                'fmt_stream_map',
-                group='fmt_stream_map'
-            )
-            fmt_list = self._html_search_regex(
-                r'"fmt_list","(?P<fmt_list>.*?)"',
-                webpage,
-                'fmt_list',
-                group='fmt_list'
-            )
-#                      timestamp = self._html_search_regex(
-#                              r'"timestamp","(?P<timestamp>.*?)"',
-#                              webpage,
-#                              'timestamp',
-#                              group='timestamp'
-#                      )
-            length_seconds = self._html_search_regex(
-                r'"length_seconds","(?P<length_seconds>.*?)"',
-                webpage,
-                'length_seconds',
-                group='length_seconds'
-            )
-        except RegexNotFoundError:
-            try:
-                reason = self._html_search_regex(
-                    r'"reason","(?P<reason>.*?)"',
-                    webpage,
-                    'reason',
-                    group='reason'
-                )
-                self.report_warning(reason)
-                return
-            except RegexNotFoundError:
-                self.report_warning('not a video')
-                return
+            '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(',')
 
-        fmt_stream_map = fmt_stream_map.split(',')
-        fmt_list = fmt_list.split(',')
         formats = []
-        for i in range(len(fmt_stream_map)):
-            fmt_id, fmt_url = fmt_stream_map[i].split('|')
-            resolution = fmt_list[i].split('/')[1]
+        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(width),
-                'height': int(height),
-                'ext': self._formats[fmt_id]['ext']
+                '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,
-#           'timestamp': int(timestamp),
-            'duration': int(length_seconds),
-            'formats': formats
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'duration': duration,
+            'formats': formats,
         }