From a56e74e2713ed45f4096735cf49d1d97b5e75389 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?D=C3=A9stin=20Reed?= Date: Wed, 28 Sep 2016 16:54:06 +0200 Subject: [PATCH] [Instagram] Extract comments --- youtube_dl/extractor/instagram.py | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py index 8f7f232be..5ebc30a10 100644 --- a/youtube_dl/extractor/instagram.py +++ b/youtube_dl/extractor/instagram.py @@ -29,6 +29,7 @@ class InstagramIE(InfoExtractor): 'uploader': 'Naomi Leonor Phan-Quang', 'like_count': int, 'comment_count': int, + 'comments': list, }, }, { # missing description @@ -44,6 +45,7 @@ class InstagramIE(InfoExtractor): 'uploader': 'Britney Spears', 'like_count': int, 'comment_count': int, + 'comments': list, }, 'params': { 'skip_download': True, @@ -101,6 +103,14 @@ def _real_extract(self, url): uploader_id = media.get('owner', {}).get('username') like_count = int_or_none(media.get('likes', {}).get('count')) comment_count = int_or_none(media.get('comments', {}).get('count')) + comments = [{ + 'author': comment.get('user', {}).get('username'), + 'author_id': comment.get('user', {}).get('id'), + 'id': comment.get('id'), + 'text': comment.get('text'), + 'timestamp': int_or_none(comment.get('created_at')), + } for comment in media.get('comments', {}).get('nodes', []) + if comment.get('text')] if not video_url: video_url = self._og_search_video_url(webpage, secure=False) @@ -131,6 +141,7 @@ def _real_extract(self, url): 'uploader': uploader, 'like_count': like_count, 'comment_count': comment_count, + 'comments': comments, }