X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Finstagram.py;h=c158f206410467e8c66a8bc2526d0436cc1a4e3c;hb=78653a33aa00ba5205940c2baac5d9f019795b88;hp=b5372bf7a24e48a347127a1dc76c9dc672b32b64;hpb=ce328530a9009ffb5f0f486fc5178520d972f07a;p=youtube-dl

diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py
index b5372bf7a..c158f2064 100644
--- a/youtube_dl/extractor/instagram.py
+++ b/youtube_dl/extractor/instagram.py
@@ -5,13 +5,14 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
+    limit_length,
 )
 
 
 class InstagramIE(InfoExtractor):
-    _VALID_URL = r'http://instagram\.com/p/(?P<id>.*?)/'
-    _TEST = {
-        'url': 'http://instagram.com/p/aye83DjauH/?foo=bar#abc',
+    _VALID_URL = r'https?://(?:www\.)?instagram\.com/p/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://instagram.com/p/aye83DjauH/?foo=bar#abc',
         'md5': '0d2da106a9d2631273e192b372806516',
         'info_dict': {
             'id': 'aye83DjauH',
@@ -20,16 +21,19 @@ class InstagramIE(InfoExtractor):
             'title': 'Video by naomipq',
             'description': 'md5:1f17f0ab29bd6fe2bfad705f58de3cb8',
         }
-    }
+    }, {
+        'url': 'https://instagram.com/p/-Cmh1cukG2/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
+
         webpage = self._download_webpage(url, video_id)
         uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"',
-            webpage, 'uploader id', fatal=False)
+                                         webpage, 'uploader id', fatal=False)
         desc = self._search_regex(r'"caption":"(.*?)"', webpage, 'description',
-            fatal=False)
+                                  fatal=False)
 
         return {
             'id': video_id,
@@ -43,9 +47,33 @@ class InstagramIE(InfoExtractor):
 
 
 class InstagramUserIE(InfoExtractor):
-    _VALID_URL = r'http://instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])'
+    _VALID_URL = r'https://instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])'
     IE_DESC = 'Instagram user profile'
     IE_NAME = 'instagram:user'
+    _TEST = {
+        'url': 'https://instagram.com/porsche',
+        'info_dict': {
+            'id': 'porsche',
+            'title': 'porsche',
+        },
+        'playlist_mincount': 2,
+        'playlist': [{
+            'info_dict': {
+                'id': '614605558512799803_462752227',
+                'ext': 'mp4',
+                'title': '#Porsche Intelligent Performance.',
+                'thumbnail': 're:^https?://.*\.jpg',
+                'uploader': 'Porsche',
+                'uploader_id': 'porsche',
+                'timestamp': 1387486713,
+                'upload_date': '20131219',
+            },
+        }],
+        'params': {
+            'extract_flat': True,
+            'skip_download': True,
+        }
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -78,11 +106,13 @@ class InstagramUserIE(InfoExtractor):
                 thumbnails_el = it.get('images', {})
                 thumbnail = thumbnails_el.get('thumbnail', {}).get('url')
 
-                title = it.get('caption', {}).get('text', it['id'])
+                # In some cases caption is null, which corresponds to None
+                # in python. As a result, it.get('caption', {}) gives None
+                title = (it.get('caption') or {}).get('text', it['id'])
 
                 entries.append({
                     'id': it['id'],
-                    'title': title,
+                    'title': limit_length(title, 80),
                     'formats': formats,
                     'thumbnail': thumbnail,
                     'webpage_url': it.get('link'),