about summary refs log tree commit diff
diff options
context:
space:
mode:
authorRoman Sebastian Karwacik <roman.karwacik@rwth-aachen.de>2020-04-12 23:27:58 +0200
committerRemita Amine <remitamine@gmail.com>2021-03-24 17:26:44 +0100
commitd1069d33b4ad3987acc2452756459065ce635d68 (patch)
treed974bd1aa4bdfa95ea798a857ea597cfa96d9f30
parenteafcadea261dba64c44c5c17ea8a47ac17256617 (diff)
downloadyoutube-dl-d1069d33b4ad3987acc2452756459065ce635d68.tar.gz
youtube-dl-d1069d33b4ad3987acc2452756459065ce635d68.tar.xz
youtube-dl-d1069d33b4ad3987acc2452756459065ce635d68.zip
[zoom] Add new extractor(closes #16597, closes #27002, closes #28531)
-rw-r--r--youtube_dl/extractor/extractors.py1
-rw-r--r--youtube_dl/extractor/zoom.py68
2 files changed, 69 insertions, 0 deletions
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index e0fd0b648..b2b39e4dd 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -1629,4 +1629,5 @@ from .zingmp3 import (
     ZingMp3IE,
     ZingMp3AlbumIE,
 )
+from .zoom import ZoomIE
 from .zype import ZypeIE
diff --git a/youtube_dl/extractor/zoom.py b/youtube_dl/extractor/zoom.py
new file mode 100644
index 000000000..db073d91d
--- /dev/null
+++ b/youtube_dl/extractor/zoom.py
@@ -0,0 +1,68 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    js_to_json,
+    parse_filesize,
+    urlencode_postdata,
+)
+
+
+class ZoomIE(InfoExtractor):
+    IE_NAME = 'zoom'
+    _VALID_URL = r'(?P<base_url>https?://(?:[^.]+\.)?zoom.us/)rec(?:ording)?/(?:play|share)/(?P<id>[A-Za-z0-9_.-]+)'
+    _TEST = {
+        'url': 'https://economist.zoom.us/rec/play/dUk_CNBETmZ5VA2BwEl-jjakPpJ3M1pcfVYAPRsoIbEByGsLjUZtaa4yCATQuOL3der8BlTwxQePl_j0.EImBkXzTIaPvdZO5',
+        'md5': 'ab445e8c911fddc4f9adc842c2c5d434',
+        'info_dict': {
+            'id': 'dUk_CNBETmZ5VA2BwEl-jjakPpJ3M1pcfVYAPRsoIbEByGsLjUZtaa4yCATQuOL3der8BlTwxQePl_j0.EImBkXzTIaPvdZO5',
+            'ext': 'mp4',
+            'title': 'China\'s "two sessions" and the new five-year plan',
+        }
+    }
+
+    def _real_extract(self, url):
+        base_url, play_id = re.match(self._VALID_URL, url).groups()
+        webpage = self._download_webpage(url, play_id)
+
+        try:
+            form = self._form_hidden_inputs('password_form', webpage)
+        except ExtractorError:
+            form = None
+        if form:
+            password = self._downloader.params.get('videopassword')
+            if not password:
+                raise ExtractorError(
+                    'This video is protected by a passcode, use the --video-password option', expected=True)
+            is_meeting = form.get('useWhichPasswd') == 'meeting'
+            validation = self._download_json(
+                base_url + 'rec/validate%s_passwd' % ('_meet' if is_meeting else ''),
+                play_id, 'Validating passcode', 'Wrong passcode', data=urlencode_postdata({
+                    'id': form[('meet' if is_meeting else 'file') + 'Id'],
+                    'passwd': password,
+                    'action': form.get('action'),
+                }))
+            if not validation.get('status'):
+                raise ExtractorError(validation['errorMessage'], expected=True)
+            webpage = self._download_webpage(url, play_id)
+
+        data = self._parse_json(self._search_regex(
+            r'(?s)window\.__data__\s*=\s*({.+?});',
+            webpage, 'data'), play_id, js_to_json)
+
+        return {
+            'id': play_id,
+            'title': data['topic'],
+            'url': data['viewMp4Url'],
+            'width': int_or_none(data.get('viewResolvtionsWidth')),
+            'height': int_or_none(data.get('viewResolvtionsHeight')),
+            'http_headers': {
+                'Referer': base_url,
+            },
+            'filesize_approx': parse_filesize(data.get('fileSize')),
+        }