summary refs log tree commit diff
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2015-02-26 01:15:08 +0100
committerPhilipp Hagemeister <phihag@phihag.de>2015-02-26 01:15:08 +0100
commitcd5b4b0bc2876e16656d33156754ce3c05aa1619 (patch)
treec79db853bcaca831f2543c0cfe0341d2dde0ff8e
parent7ef822021b24a541f880d9b60f03cc17d49dfb30 (diff)
parent1b40dc92eb27b2a3f299157f83bfc8e95ca42268 (diff)
downloadyoutube-dl-cd5b4b0bc2876e16656d33156754ce3c05aa1619.tar.gz
youtube-dl-cd5b4b0bc2876e16656d33156754ce3c05aa1619.tar.xz
youtube-dl-cd5b4b0bc2876e16656d33156754ce3c05aa1619.zip
Merge remote-tracking branch 'duncankl/airmozilla'
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/airmozilla.py73
2 files changed, 74 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 40fc92cf7..67dca82ae 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -8,6 +8,7 @@ from .adobetv import AdobeTVIE
 from .adultswim import AdultSwimIE
 from .aftenposten import AftenpostenIE
 from .aftonbladet import AftonbladetIE
+from .airmozilla import AirMozillaIE
 from .aljazeera import AlJazeeraIE
 from .alphaporno import AlphaPornoIE
 from .anitube import AnitubeIE
diff --git a/youtube_dl/extractor/airmozilla.py b/youtube_dl/extractor/airmozilla.py
new file mode 100644
index 000000000..44c20f886
--- /dev/null
+++ b/youtube_dl/extractor/airmozilla.py
@@ -0,0 +1,73 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import parse_iso8601
+
+
+class AirMozillaIE(InfoExtractor):
+    _VALID_URL = r'https?://air\.mozilla\.org/(?P<id>[0-9a-z-]+)/?'
+    _TEST = {
+        'url': 'https://air.mozilla.org/privacy-lab-a-meetup-for-privacy-minded-people-in-san-francisco/',
+        'md5': '2e3e7486ba5d180e829d453875b9b8bf',
+        'info_dict': {
+            'id': '6x4q2w',
+            'ext': 'mp4',
+            'title': 'Privacy Lab - a meetup for privacy minded people in San Francisco',
+            'thumbnail': 're:https://\w+\.cloudfront\.net/6x4q2w/poster\.jpg\?t=\d+',
+            'description': 'Brings together privacy professionals and others interested in privacy at for-profits, non-profits, and NGOs in an effort to contribute to the state of the ecosystem...',
+            'timestamp': 1422487800,
+            'upload_date': '20150128',
+            'location': 'SFO Commons',
+            'duration': 3780,
+            'view_count': int,
+            'categories': ['Main'],
+        }
+    }
+
+    _QUALITY_MAP = {
+        '360p': 0,
+        '576p': 1,
+        '640p': 2,
+        '720p': 3,
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        video_id = self._html_search_regex(r'//vid.ly/(.*?)/embed', webpage, 'id')
+
+        embed_script = self._download_webpage('https://vid.ly/{0}/embed'.format(video_id), video_id)
+        jwconfig = self._search_regex(r'\svar jwconfig = (\{.*?\});\s', embed_script, 'metadata')
+        metadata = self._parse_json(jwconfig, video_id)
+
+        formats = []
+        for source in metadata['playlist'][0]['sources']:
+            fmt = {
+                'url': source['file'],
+                'ext': source['type'],
+                'format_id': self._search_regex(r'&format=(.*)$', source['file'], 'video format'),
+                'resolution': source['label'],
+                'quality': self._QUALITY_MAP.get(source['label'], -1),
+            }
+            formats.append(fmt)
+        self._sort_formats(formats)
+
+        duration_match = re.search(r'Duration:(?: (?P<H>\d+) hours?)?(?: (?P<M>\d+) minutes?)?', webpage)
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage),
+            'formats': formats,
+            'url': self._og_search_url(webpage),
+            'display_id': display_id,
+            'thumbnail': metadata['playlist'][0]['image'],
+            'description': self._og_search_description(webpage),
+            'timestamp': parse_iso8601(self._html_search_regex(r'<time datetime="(.*?)"', webpage, 'timestamp')),
+            'location': self._html_search_regex(r'Location: (.*)', webpage, 'location', default=None),
+            'duration': int(duration_match.groupdict()['H'] or 0) * 3600 + int(duration_match.groupdict()['M'] or 0) * 60,
+            'view_count': int(self._html_search_regex(r'Views since archived: ([0-9]+)', webpage, 'view count')),
+            'categories': re.findall(r'<a href=".*?" class="channel">(.*?)</a>', webpage),
+        }