d/control: Add build-dependency on dh-python as per warning from dh_python2.

[youtubedl] / youtube_dl / extractor / vine.py

diff --git a/youtube_dl/extractor/vine.py b/youtube_dl/extractor/vine.py
index 42995226e584b0ce4e0d207b6b702157ec6f4030..c733a48fa26edce6b219d3bf2404267b8c346bf6 100644 (file)
--- a/youtube_dl/extractor/vine.py
+++ b/youtube_dl/extractor/vine.py
@@ -1,7 +1,6 @@
 from __future__ import unicode_literals
 
 import re
 from __future__ import unicode_literals
 
 import re

-import json

 import itertools
 
 from .common import InfoExtractor
 import itertools
 
 from .common import InfoExtractor


@@ -9,46 +8,74 @@ from ..utils import unified_strdate
 
 
 class VineIE(InfoExtractor):
 
 
 class VineIE(InfoExtractor):

-    _VALID_URL = r'https?://(?:www\.)?vine\.co/v/(?P<id>\w+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?vine\.co/(?:v|oembed)/(?P<id>\w+)'
+    _TESTS = [{

         'url': 'https://vine.co/v/b9KOOWX7HUx',
         'md5': '2f36fed6235b16da96ce9b4dc890940d',
         'info_dict': {
             'id': 'b9KOOWX7HUx',
             'ext': 'mp4',
             'title': 'Chicken.',
         'url': 'https://vine.co/v/b9KOOWX7HUx',
         'md5': '2f36fed6235b16da96ce9b4dc890940d',
         'info_dict': {
             'id': 'b9KOOWX7HUx',
             'ext': 'mp4',
             'title': 'Chicken.',

+            'alt_title': 'Vine by Jack Dorsey',

             'description': 'Chicken.',
             'upload_date': '20130519',
             'uploader': 'Jack Dorsey',
             'uploader_id': '76',
         },
             'description': 'Chicken.',
             'upload_date': '20130519',
             'uploader': 'Jack Dorsey',
             'uploader_id': '76',
         },

-    }
+    }, {
+        'url': 'https://vine.co/v/MYxVapFvz2z',
+        'md5': '7b9a7cbc76734424ff942eb52c8f1065',
+        'info_dict': {
+            'id': 'MYxVapFvz2z',
+            'ext': 'mp4',
+            'title': 'Fuck Da Police #Mikebrown #justice #ferguson #prayforferguson #protesting #NMOS14',
+            'alt_title': 'Vine by Luna',
+            'description': 'Fuck Da Police #Mikebrown #justice #ferguson #prayforferguson #protesting #NMOS14',
+            'upload_date': '20140815',
+            'uploader': 'Luna',
+            'uploader_id': '1102363502380728320',
+        },
+    }, {
+        'url': 'https://vine.co/v/bxVjBbZlPUH',
+        'md5': 'ea27decea3fa670625aac92771a96b73',
+        'info_dict': {
+            'id': 'bxVjBbZlPUH',
+            'ext': 'mp4',
+            'title': '#mw3 #ac130 #killcam #angelofdeath',
+            'alt_title': 'Vine by Z3k3',
+            'description': '#mw3 #ac130 #killcam #angelofdeath',
+            'upload_date': '20130430',
+            'uploader': 'Z3k3',
+            'uploader_id': '936470460173008896',
+        },
+    }, {
+        'url': 'https://vine.co/oembed/MYxVapFvz2z.json',
+        'only_matching': True,
+    }]

 
     def _real_extract(self, url):
 
     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('https://vine.co/v/' + video_id, video_id)
 
         webpage = self._download_webpage('https://vine.co/v/' + video_id, video_id)
 

-        data = json.loads(self._html_search_regex(
-            r'window\.POST_DATA = { %s: ({.+?}) }' % video_id, webpage, 'vine data'))
+        data = self._parse_json(
+            self._html_search_regex(
+                r'window\.POST_DATA = { %s: ({.+?}) };\s*</script>' % video_id,
+                webpage, 'vine data'),
+            video_id)

 
 

-        formats = [
-            {
-                'url': data['videoLowURL'],
-                'ext': 'mp4',
-                'format_id': 'low',
-            },
-            {
-                'url': data['videoUrl'],
-                'ext': 'mp4',
-                'format_id': 'standard',
-            }
-        ]
+        formats = [{
+            'format_id': '%(format)s-%(rate)s' % f,
+            'vcodec': f['format'],
+            'quality': f['rate'],
+            'url': f['videoUrl'],
+        } for f in data['videoUrls']]
+
+        self._sort_formats(formats)

 
         return {
             'id': video_id,
             'title': self._og_search_title(webpage),
 
         return {
             'id': video_id,
             'title': self._og_search_title(webpage),

+            'alt_title': self._og_search_description(webpage, default=None),

             'description': data['description'],
             'thumbnail': data['thumbnailUrl'],
             'upload_date': unified_strdate(data['created']),
             'description': data['description'],
             'thumbnail': data['thumbnailUrl'],
             'upload_date': unified_strdate(data['created']),


@@ -63,29 +90,36 @@ class VineIE(InfoExtractor):
 
 class VineUserIE(InfoExtractor):
     IE_NAME = 'vine:user'
 
 class VineUserIE(InfoExtractor):
     IE_NAME = 'vine:user'

-    _VALID_URL = r'(?:https?://)?vine\.co/(?P<user>[^/]+)/?(\?.*)?$'
+    _VALID_URL = r'(?:https?://)?vine\.co/(?P<u>u/)?(?P<user>[^/]+)/?(\?.*)?$'

     _VINE_BASE_URL = "https://vine.co/"
     _VINE_BASE_URL = "https://vine.co/"

-    _TEST = {
-        'url': 'https://vine.co/Visa',
-        'info_dict': {
-            'id': 'Visa',
+    _TESTS = [
+        {
+            'url': 'https://vine.co/Visa',
+            'info_dict': {
+                'id': 'Visa',
+            },
+            'playlist_mincount': 46,
+        },
+        {
+            'url': 'https://vine.co/u/941705360593584128',
+            'only_matching': True,

         },
         },

-        'playlist_mincount': 46,
-    }
+    ]

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         user = mobj.group('user')
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         user = mobj.group('user')

+        u = mobj.group('u')

 
 

-        profile_url = "%sapi/users/profiles/vanity/%s" % (
-            self._VINE_BASE_URL, user)
+        profile_url = "%sapi/users/profiles/%s%s" % (
+            self._VINE_BASE_URL, 'vanity/' if not u else '', user)

         profile_data = self._download_json(
             profile_url, user, note='Downloading user profile data')
 
         user_id = profile_data['data']['userId']
         timeline_data = []
         for pagenum in itertools.count(1):
         profile_data = self._download_json(
             profile_url, user, note='Downloading user profile data')
 
         user_id = profile_data['data']['userId']
         timeline_data = []
         for pagenum in itertools.count(1):

-            timeline_url = "%sapi/timelines/users/%s?page=%s" % (
+            timeline_url = "%sapi/timelines/users/%s?page=%s&size=100" % (

                 self._VINE_BASE_URL, user_id, pagenum)
             timeline_page = self._download_json(
                 timeline_url, user, note='Downloading page %d' % pagenum)
                 self._VINE_BASE_URL, user_id, pagenum)
             timeline_page = self._download_json(
                 timeline_url, user, note='Downloading page %d' % pagenum)