X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Finstagram.py;h=c158f206410467e8c66a8bc2526d0436cc1a4e3c;hb=3047121c639428235191ff5f7afbda7ecda38779;hp=65f6ca103973bb25c016ae92fcb551c65def31d1;hpb=40b96352c99953aec9272574729077c06c235747;p=youtube-dl

diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py
index 65f6ca103..c158f2064 100644
--- a/youtube_dl/extractor/instagram.py
+++ b/youtube_dl/extractor/instagram.py
@@ -3,13 +3,16 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import int_or_none
+from ..utils import (
+    int_or_none,
+    limit_length,
+)
 
 
 class InstagramIE(InfoExtractor):
-    _VALID_URL = r'https?://instagram\.com/p/(?P<id>[\da-zA-Z]+)'
-    _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',
@@ -18,7 +21,10 @@ class InstagramIE(InfoExtractor):
             'title': 'Video by naomipq',
             'description': 'md5:1f17f0ab29bd6fe2bfad705f58de3cb8',
         }
-    }
+    }, {
+        'url': 'https://instagram.com/p/-Cmh1cukG2/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -41,11 +47,11 @@ 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': 'http://instagram.com/porsche',
+        'url': 'https://instagram.com/porsche',
         'info_dict': {
             'id': 'porsche',
             'title': 'porsche',
@@ -100,11 +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'),