[Flipagram] add new extractor

saw there was another pull request for an extractor for the website, but it does not extract all the necessary metadata, and has been inactive for a period of time

youtube_dl/extractor/common.py

@@ -833,6 +833,13 @@ class InfoExtractor(object):
                     'title': unescapeHTML(json_ld.get('headline')),
                     'description': unescapeHTML(json_ld.get('articleBody')),
                 })
+            elif item_type == 'VideoObject':
+                info.update({
+                    'title': unescapeHTML(json_ld.get('name')),
+                    'description': unescapeHTML(json_ld.get('description')),
+                    'upload_date': unified_strdate(json_ld.get('upload_date')),
+                    'url': unescapeHTML(json_ld.get('contentUrl')),
+                })
         return dict((k, v) for k, v in info.items() if v is not None)
 
     @staticmethod

youtube_dl/extractor/extractors.py

@@ -240,6 +240,7 @@ from .fivemin import FiveMinIE
 from .fivetv import FiveTVIE
 from .fktv import FKTVIE
 from .flickr import FlickrIE
+from .flipagram import FlipagramIE
 from .folketinget import FolketingetIE
 from .footyroom import FootyRoomIE
 from .formula1 import Formula1IE

youtube_dl/extractor/flipagram.py

@@ -0,0 +1,106 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import time
+from .common import InfoExtractor
+
+from ..utils import (
+    parse_iso8601,
+    unified_strdate,
+    int_or_none,
+)
+
+
+class FlipagramIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?flipagram\.com/f/(?P<id>[^/?_]+)'
+    _TESTS = [{
+        'url': 'https://flipagram.com/f/myrWjW9RJw',
+        'md5': '541988fb6c4c7c375215ea22a4a21841',
+        'info_dict': {
+            'id': 'myrWjW9RJw',
+            'title': 'Flipagram by crystaldolce featuring King and Lionheart by Of Monsters and Men',
+            'description': 'Herbie\'s first bannana🍌🐢🍌.  #animals #pets #reptile #tortoise #sulcata #tort #justatreat #snacktime #bannanas #rescuepets  #ofmonstersandmen  @animals',
+            'ext': 'mp4',
+            'uploader': 'Crystal Dolce',
+            'creator': 'Crystal Dolce',
+            'uploader_id': 'crystaldolce',
+        }
+    }, {
+        'url': 'https://flipagram.com/f/nyvTSJMKId',
+        'only_matching': True,
+    }]
+
+    def c_date_to_iso(self, c_date):
+        'Convert dates in format \'04/25/2016 00:23:24 UTC\' to ISO8601.'
+        return time.strftime('%Y-%m-%dT%H:%M:%S', time.strptime(c_date, '%m/%d/%Y %H:%M:%S %Z'))
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        self.report_extraction(video_id)
+        user_data = self._parse_json(self._search_regex(r'window.reactH2O\s*=\s*({.+});', webpage, 'user data'), video_id)
+        content_data = self._search_json_ld(webpage, video_id)
+
+        flipagram = user_data.get('flipagram', {})
+        counts = flipagram.get('counts', {})
+        user = flipagram.get('user', {})
+        video = flipagram.get('video', {})
+
+        thumbnails = []
+        for cover in flipagram.get('covers', []):
+            if not cover.get('url'):
+                continue
+            thumbnails.append({
+                'url': self._proto_relative_url(cover.get('url')),
+                'width': int_or_none(cover.get('width')),
+                'height': int_or_none(cover.get('height')),
+            })
+
+        comments = []
+        for comment in user_data.get('comments', {}).get(video_id, {}).get('items', []):
+            text = comment.get('comment', [])
+            comments.append({
+                'author': comment.get('user', {}).get('name'),
+                'author_id': comment.get('user', {}).get('username'),
+                'id': comment.get('id'),
+                'text': text[0] if text else '',
+                'timestamp': parse_iso8601(self.c_date_to_iso(comment.get('created', ''))),
+            })
+
+        tags = [tag for item in flipagram['story'][1:] for tag in item]
+
+        formats = []
+        if flipagram.get('music', {}).get('track', {}).get('previewUrl', {}):
+             formats.append({
+                'url': flipagram.get('music').get('track').get('previewUrl'),
+                'ext': 'm4a',
+                'vcodec': 'none',
+            })
+
+        formats.append({
+            'url': video.get('url'),
+            'ext': 'mp4',
+            'width': int_or_none(video.get('width')),
+            'height': int_or_none(video.get('height')),
+            'filesize': int_or_none(video.get('size')),
+        })
+
+        return {
+            'id': video_id,
+            'title': content_data.get('title'),
+            'formats': formats,
+            'ext': 'mp4',
+            'thumbnails': thumbnails,
+            'description': content_data.get('description'),
+            'uploader': user.get('name'),
+            'creator': user.get('name'),
+            'timestamp': parse_iso8601(flipagram.get('iso801Created')),
+            'upload_date': unified_strdate(flipagram.get('created')),
+            'uploader_id': user.get('username'),
+            'view_count': int_or_none(counts.get('plays')),
+            'repost_count': int_or_none(counts.get('reflips')),
+            'comment_count': int_or_none(counts.get('comments')),
+            'comments': comments,
+            'tags': tags,
+        }