aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl')
-rw-r--r--youtube_dl/YoutubeDL.py16
-rw-r--r--youtube_dl/extractor/__init__.py2
-rw-r--r--youtube_dl/extractor/instagram.py68
3 files changed, 78 insertions, 8 deletions
diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py
index c5d08b0bb..d18d6dd00 100644
--- a/youtube_dl/YoutubeDL.py
+++ b/youtube_dl/YoutubeDL.py
@@ -512,13 +512,7 @@ class YoutubeDL(object):
'_type': 'compat_list',
'entries': ie_result,
}
- self.add_extra_info(ie_result,
- {
- 'extractor': ie.IE_NAME,
- 'webpage_url': url,
- 'webpage_url_basename': url_basename(url),
- 'extractor_key': ie.ie_key(),
- })
+ self.add_default_extra_info(ie_result, ie, url)
if process:
return self.process_ie_result(ie_result, download, extra_info)
else:
@@ -537,6 +531,14 @@ class YoutubeDL(object):
else:
self.report_error('no suitable InfoExtractor for URL %s' % url)
+ def add_default_extra_info(self, ie_result, ie, url):
+ self.add_extra_info(ie_result, {
+ 'extractor': ie.IE_NAME,
+ 'webpage_url': url,
+ 'webpage_url_basename': url_basename(url),
+ 'extractor_key': ie.ie_key(),
+ })
+
def process_ie_result(self, ie_result, download=True, extra_info={}):
"""
Take the result of the ie(may be modified) and resolve all unresolved
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index b5c8ef682..3e728e876 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -112,7 +112,7 @@ from .imdb import (
)
from .ina import InaIE
from .infoq import InfoQIE
-from .instagram import InstagramIE
+from .instagram import InstagramIE, InstagramUserIE
from .internetvideoarchive import InternetVideoArchiveIE
from .iprima import IPrimaIE
from .ivi import (
diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py
index 63141af27..994f0e4ae 100644
--- a/youtube_dl/extractor/instagram.py
+++ b/youtube_dl/extractor/instagram.py
@@ -3,6 +3,9 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
+from ..utils import (
+ int_or_none,
+)
class InstagramIE(InfoExtractor):
@@ -37,3 +40,68 @@ class InstagramIE(InfoExtractor):
'uploader_id': uploader_id,
'description': desc,
}
+
+
+class InstagramUserIE(InfoExtractor):
+ _VALID_URL = r'http://instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])'
+ IE_DESC = 'Instagram user profile'
+ IE_NAME = 'instagram:user'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ uploader_id = mobj.group('username')
+
+ entries = []
+ page_count = 0
+ media_url = 'http://instagram.com/%s/media' % uploader_id
+ while True:
+ page = self._download_json(
+ media_url, uploader_id,
+ note='Downloading page %d ' % (page_count + 1),
+ )
+ page_count += 1
+
+ for it in page['items']:
+ if it.get('type') != 'video':
+ continue
+ like_count = int_or_none(it.get('likes', {}).get('count'))
+ user = it.get('user', {})
+
+ formats = [{
+ 'format_id': k,
+ 'height': v.get('height'),
+ 'width': v.get('width'),
+ 'url': v['url'],
+ } for k, v in it['videos'].items()]
+ self._sort_formats(formats)
+
+ thumbnails_el = it.get('images', {})
+ thumbnail = thumbnails_el.get('thumbnail', {}).get('url')
+
+ title = it.get('caption', {}).get('text', it['id'])
+
+ entries.append({
+ 'id': it['id'],
+ 'title': title,
+ 'formats': formats,
+ 'thumbnail': thumbnail,
+ 'webpage_url': it.get('link'),
+ 'uploader': user.get('full_name'),
+ 'uploader_id': user.get('username'),
+ 'like_count': like_count,
+ 'upload_timestamp': int_or_none(it.get('created_time')),
+ })
+
+ if not page['items']:
+ break
+ max_id = page['items'][-1]['id']
+ media_url = (
+ 'http://instagram.com/%s/media?max_id=%s' % (
+ uploader_id, max_id))
+
+ return {
+ '_type': 'playlist',
+ 'entries': entries,
+ 'id': uploader_id,
+ 'title': uploader_id,
+ }