Merge branch 'lecture2go' of https://github.com/nichdu/youtube-dl into nichdu-lecture2go

[youtube-dl] / youtube_dl / extractor / instagram.py

diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py
index 65f6ca103973bb25c016ae92fcb551c65def31d1..3d78f78c46d1ad004339bc33ebcb09d1286e5092 100644 (file)
--- 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]+)'
+    _VALID_URL = r'https://instagram\.com/p/(?P<id>[\da-zA-Z]+)'
     _TEST = {
-        'url': 'http://instagram.com/p/aye83DjauH/?foo=bar#abc',
+        'url': 'https://instagram.com/p/aye83DjauH/?foo=bar#abc',
         'md5': '0d2da106a9d2631273e192b372806516',
         'info_dict': {
             'id': 'aye83DjauH',
@@ -41,11 +44,11 @@ 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 +103,13 @@ 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'),