From 3fee7f636cb63e6cb785b07e4ffea3cc91981525 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?D=C3=A9stin=20Reed?= Date: Sat, 25 Jun 2016 19:01:47 +0200 Subject: [PATCH] [flipagram] Add extractor --- youtube_dl/extractor/common.py | 7 ++ youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/flipagram.py | 103 +++++++++++++++++++++++++++++ 3 files changed, 111 insertions(+) create mode 100644 youtube_dl/extractor/flipagram.py diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index be2b6ff66..b5fce5de2 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -837,6 +837,13 @@ 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 diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 12cc1b5f7..9f70ce752 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -256,6 +256,7 @@ 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 diff --git a/youtube_dl/extractor/flipagram.py b/youtube_dl/extractor/flipagram.py new file mode 100644 index 000000000..7143126b5 --- /dev/null +++ b/youtube_dl/extractor/flipagram.py @@ -0,0 +1,103 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + +from ..utils import ( + int_or_none, + parse_iso8601, + unified_strdate, + unified_timestamp, +) + + +class FlipagramIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?flipagram\.com/f/(?P[^/?_]+)' + _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 _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')), + }) + + # Note that this only retrieves comments that are initally loaded. + # For videos with large amounts of comments, most won't be retrieved. + 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': unified_timestamp(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['title'], + 'formats': formats, + '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, + }