From 1db3d482185261152aa40d0935a88add504bc69d Mon Sep 17 00:00:00 2001
From: gkoelln <gkoelln7@gmail.com>
Date: Wed, 25 Jan 2017 10:49:24 -0600
Subject: [PATCH 01/11] [Bandcamp] Extract additional fields (#1)

* [bandcamp] Add additional extraction fields

Adding additional extraction fields

* [bandcamp] remove redundant changes

Removed redundant changes

* [bandcamp] Remove extra spaces

Removed extra spaces

* [bandcamp] Minor corrections

Correct order of return fields, minimize coding lines
---
 youtube_dl/extractor/bandcamp.py | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py
index 88c590e98..8861c8b35 100644
--- a/youtube_dl/extractor/bandcamp.py
+++ b/youtube_dl/extractor/bandcamp.py
@@ -47,6 +47,15 @@ class BandcampIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         title = mobj.group('title')
         webpage = self._download_webpage(url, title)
+        album = self._search_regex(
+            r'(?ms).*?title\s*?:\s*?"(?P<album>.*?)",',
+            webpage, 'album')
+        album_artist = self._search_regex(
+            r'(?ms)var EmbedData = .*?[{,]\s*artist:\s*?"(?P<album_artist>.*?)",$',
+            webpage, 'album artist')
+        release_year = self._search_regex(
+            r'(?ms).*?release_date"?:\s*?"\d+ \w+ (?P<release_year>\d+)\s*?.*?GMT",',
+            webpage, 'release year')
         m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
         if not m_download:
             m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage)
@@ -77,6 +86,12 @@ class BandcampIE(InfoExtractor):
                     'title': data['title'],
                     'formats': formats,
                     'duration': float_or_none(data.get('duration')),
+                    'track': data['title'],
+                    'track_number': data['track_num'],
+                    'track_id': track_id,
+                    'album': album,
+                    'album_artist': album_artist,
+                    'release_year': release_year,
                 }
             else:
                 raise ExtractorError('No free songs found')
@@ -86,6 +101,10 @@ class BandcampIE(InfoExtractor):
             r'(?ms)var TralbumData = .*?[{,]\s*id: (?P<id>\d+),?$',
             webpage, 'video id')
 
+        track_number = self._search_regex(
+            r'"track_num":(?P<track_number>\d+),',
+            webpage, 'track number')
+
         download_webpage = self._download_webpage(
             download_link, video_id, 'Downloading free downloads page')
 
@@ -148,6 +167,10 @@ class BandcampIE(InfoExtractor):
             'artist': artist,
             'track': track,
             'formats': formats,
+            'track_number': track_number,
+            'album': album,
+            'album_artist': album_artist,
+            'release_year': release_year,
         }
 
 
@@ -233,5 +256,6 @@ class BandcampAlbumIE(InfoExtractor):
             'uploader_id': uploader_id,
             'id': playlist_id,
             'title': title,
+            'album': title,
             'entries': entries,
         }

From b6661befd5bb8bafa980c023e0993ca1403eb0cb Mon Sep 17 00:00:00 2001
From: gkoelln <gkoelln7@gmail.com>
Date: Wed, 25 Jan 2017 11:22:08 -0600
Subject: [PATCH 02/11] [bandcamp] Make new extraction fields optional

Made new extraction fields optional
---
 youtube_dl/extractor/bandcamp.py | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py
index 8861c8b35..5f87ae3ac 100644
--- a/youtube_dl/extractor/bandcamp.py
+++ b/youtube_dl/extractor/bandcamp.py
@@ -49,13 +49,13 @@ class BandcampIE(InfoExtractor):
         webpage = self._download_webpage(url, title)
         album = self._search_regex(
             r'(?ms).*?title\s*?:\s*?"(?P<album>.*?)",',
-            webpage, 'album')
+            webpage, 'album', fatal=False)
         album_artist = self._search_regex(
             r'(?ms)var EmbedData = .*?[{,]\s*artist:\s*?"(?P<album_artist>.*?)",$',
-            webpage, 'album artist')
+            webpage, 'album artist', fatal=False)
         release_year = self._search_regex(
             r'(?ms).*?release_date"?:\s*?"\d+ \w+ (?P<release_year>\d+)\s*?.*?GMT",',
-            webpage, 'release year')
+            webpage, 'release year', fatal=False)
         m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
         if not m_download:
             m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage)
@@ -103,7 +103,7 @@ class BandcampIE(InfoExtractor):
 
         track_number = self._search_regex(
             r'"track_num":(?P<track_number>\d+),',
-            webpage, 'track number')
+            webpage, 'track number', fatal=False)
 
         download_webpage = self._download_webpage(
             download_link, video_id, 'Downloading free downloads page')

From 150fa802eda31fbec0a4e7f7e0d4a2da10e9ad2b Mon Sep 17 00:00:00 2001
From: gkoelln <gkoelln7@gmail.com>
Date: Thu, 26 Jan 2017 10:15:03 -0600
Subject: [PATCH 03/11] [bandcamp] Adhere to youtube-dl specifications

Making optional fields optional
---
 youtube_dl/extractor/bandcamp.py | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py
index 5f87ae3ac..8fbadc644 100644
--- a/youtube_dl/extractor/bandcamp.py
+++ b/youtube_dl/extractor/bandcamp.py
@@ -62,8 +62,7 @@ class BandcampIE(InfoExtractor):
             if m_trackinfo:
                 json_code = m_trackinfo.group(1)
                 data = json.loads(json_code)[0]
-                track_id = compat_str(data['id'])
-
+                
                 if not data.get('file'):
                     raise ExtractorError('Not streamable', video_id=track_id, expected=True)
 
@@ -86,9 +85,9 @@ class BandcampIE(InfoExtractor):
                     'title': data['title'],
                     'formats': formats,
                     'duration': float_or_none(data.get('duration')),
-                    'track': data['title'],
-                    'track_number': data['track_num'],
-                    'track_id': track_id,
+                    'track': data.get('title'),
+                    'track_number': data.get('track_num'),
+                    'track_id': data.get('id'),
                     'album': album,
                     'album_artist': album_artist,
                     'release_year': release_year,

From 3ca8c223150a289f57594da5447c2c59b5eeb4a4 Mon Sep 17 00:00:00 2001
From: gkoelln <gkoelln7@gmail.com>
Date: Thu, 26 Jan 2017 10:28:00 -0600
Subject: [PATCH 04/11] [bandcamp] add extracted fields

Fixed what I broke in the id fields
---
 youtube_dl/extractor/bandcamp.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py
index 8fbadc644..3b2e482ff 100644
--- a/youtube_dl/extractor/bandcamp.py
+++ b/youtube_dl/extractor/bandcamp.py
@@ -62,7 +62,8 @@ class BandcampIE(InfoExtractor):
             if m_trackinfo:
                 json_code = m_trackinfo.group(1)
                 data = json.loads(json_code)[0]
-                
+                track_id = compat_str(data['id'])
+
                 if not data.get('file'):
                     raise ExtractorError('Not streamable', video_id=track_id, expected=True)
 
@@ -87,7 +88,7 @@ class BandcampIE(InfoExtractor):
                     'duration': float_or_none(data.get('duration')),
                     'track': data.get('title'),
                     'track_number': data.get('track_num'),
-                    'track_id': data.get('id'),
+                    'track_id': track_id,
                     'album': album,
                     'album_artist': album_artist,
                     'release_year': release_year,

From 8866c7594bd08c1f46c8287ccc79fe59596cba65 Mon Sep 17 00:00:00 2001
From: gkoelln <gkoelln7@gmail.com>
Date: Thu, 26 Jan 2017 13:27:56 -0600
Subject: [PATCH 05/11] [bandbamp] Add track_id to free download

Added track_id to free download
---
 youtube_dl/extractor/bandcamp.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py
index 3b2e482ff..8b72e60bc 100644
--- a/youtube_dl/extractor/bandcamp.py
+++ b/youtube_dl/extractor/bandcamp.py
@@ -168,6 +168,7 @@ class BandcampIE(InfoExtractor):
             'track': track,
             'formats': formats,
             'track_number': track_number,
+			'track_id': video_id,
             'album': album,
             'album_artist': album_artist,
             'release_year': release_year,

From 61103eee0a39bb929a4402e7a27d6f9be5a3d982 Mon Sep 17 00:00:00 2001
From: gkoelln <gkoelln7@gmail.com>
Date: Thu, 26 Jan 2017 13:29:23 -0600
Subject: [PATCH 06/11] [bandcamp] Replace tabs with spaces

My editor puts tabs and I forgot to replace them with spaces earlier
---
 youtube_dl/extractor/bandcamp.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py
index 8b72e60bc..7579c4108 100644
--- a/youtube_dl/extractor/bandcamp.py
+++ b/youtube_dl/extractor/bandcamp.py
@@ -168,7 +168,7 @@ class BandcampIE(InfoExtractor):
             'track': track,
             'formats': formats,
             'track_number': track_number,
-			'track_id': video_id,
+            'track_id': video_id,
             'album': album,
             'album_artist': album_artist,
             'release_year': release_year,

From 45d8613023af808e0cc8e180fb83d612cc3b4b92 Mon Sep 17 00:00:00 2001
From: gkoelln <gkoelln7@gmail.com>
Date: Fri, 27 Jan 2017 15:27:10 -0600
Subject: [PATCH 07/11] [ShoutFactoryTV] New extractor

New extractor
---
 youtube_dl/extractor/shoutfactorytv.py | 54 ++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)
 create mode 100644 youtube_dl/extractor/shoutfactorytv.py

diff --git a/youtube_dl/extractor/shoutfactorytv.py b/youtube_dl/extractor/shoutfactorytv.py
new file mode 100644
index 000000000..740138c81
--- /dev/null
+++ b/youtube_dl/extractor/shoutfactorytv.py
@@ -0,0 +1,54 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    parse_m3u8_attributes,
+)
+
+
+class ShoutFactoryTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?shoutfactorytv\.com/.*?/(?P<id>[0-9a-d]+)'
+    _TEST = {
+        'url': 'http://www.shoutfactorytv.com/mst3k-shorts/mst3k-short-x-marks-the-spot/57473979e0a6b40d7300809a',
+        'md5': 'a04c5394947cead82be3808ec6285f71',
+        'info_dict': {
+            'id': '57473979e0a6b40d7300809a',
+            'ext': 'mp4',
+            'title': 'MST3K Short: X Marks The Spot',
+            'series': 'MST3K Shorts',
+            'description': 'Poor Joe gets grilled in a heavenly court in this WWII era film promoting road safety in New Jersey.',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(
+            r'<h2><span>(.+)</span>.+</h2>', webpage, 'title')
+        series = self._html_search_regex(
+            r'<h2><span>.+</span> (.+)</h2>', webpage, 'series', default=None)
+		
+        player_embed = re.search(
+            r'<script src=(["\'])(?P<javascript>https://player.zype.com\S+)\1', webpage)
+        if not player_embed:
+            raise ExtractorError('Could not extract player\'s JavaScript.')
+        javascript = player_embed.group('javascript')
+        download_js = self._download_webpage(
+            javascript, video_id, 'Downloading JavaScript page')
+        
+        m3u8 = self._html_search_regex(
+            r"source0.src = '(.*?)'", download_js, 'm3u8')
+        formats = self._extract_m3u8_formats(m3u8, video_id, 'mp4')
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+			'series': series,
+        }

From 77f2de2589c6ccf5a460d17b8d48cb722f6dbb1a Mon Sep 17 00:00:00 2001
From: gkoelln <gkoelln7@gmail.com>
Date: Fri, 27 Jan 2017 15:29:16 -0600
Subject: [PATCH 08/11] Add ShoutFactoryTV extractor

---
 youtube_dl/extractor/extractors.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 5ba8efb0e..7c600a22e 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -823,6 +823,7 @@ from .shared import (
     SharedIE,
     VivoIE,
 )
+from .shoutfactorytv import ShoutFactoryTVIE
 from .showroomlive import ShowRoomLiveIE
 from .sina import SinaIE
 from .sixplay import SixPlayIE

From 5b72f6a835d84687ba7e60ff4a8fcccd70975997 Mon Sep 17 00:00:00 2001
From: gkoelln <gkoelln7@gmail.com>
Date: Fri, 27 Jan 2017 15:34:27 -0600
Subject: [PATCH 09/11] Reverting to master branch

Reverting to master branch
---
 youtube_dl/extractor/bandcamp.py | 27 +--------------------------
 1 file changed, 1 insertion(+), 26 deletions(-)

diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py
index 7579c4108..045ea6f6f 100644
--- a/youtube_dl/extractor/bandcamp.py
+++ b/youtube_dl/extractor/bandcamp.py
@@ -47,15 +47,6 @@ class BandcampIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         title = mobj.group('title')
         webpage = self._download_webpage(url, title)
-        album = self._search_regex(
-            r'(?ms).*?title\s*?:\s*?"(?P<album>.*?)",',
-            webpage, 'album', fatal=False)
-        album_artist = self._search_regex(
-            r'(?ms)var EmbedData = .*?[{,]\s*artist:\s*?"(?P<album_artist>.*?)",$',
-            webpage, 'album artist', fatal=False)
-        release_year = self._search_regex(
-            r'(?ms).*?release_date"?:\s*?"\d+ \w+ (?P<release_year>\d+)\s*?.*?GMT",',
-            webpage, 'release year', fatal=False)
         m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
         if not m_download:
             m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage)
@@ -86,12 +77,6 @@ class BandcampIE(InfoExtractor):
                     'title': data['title'],
                     'formats': formats,
                     'duration': float_or_none(data.get('duration')),
-                    'track': data.get('title'),
-                    'track_number': data.get('track_num'),
-                    'track_id': track_id,
-                    'album': album,
-                    'album_artist': album_artist,
-                    'release_year': release_year,
                 }
             else:
                 raise ExtractorError('No free songs found')
@@ -101,10 +86,6 @@ class BandcampIE(InfoExtractor):
             r'(?ms)var TralbumData = .*?[{,]\s*id: (?P<id>\d+),?$',
             webpage, 'video id')
 
-        track_number = self._search_regex(
-            r'"track_num":(?P<track_number>\d+),',
-            webpage, 'track number', fatal=False)
-
         download_webpage = self._download_webpage(
             download_link, video_id, 'Downloading free downloads page')
 
@@ -167,11 +148,6 @@ class BandcampIE(InfoExtractor):
             'artist': artist,
             'track': track,
             'formats': formats,
-            'track_number': track_number,
-            'track_id': video_id,
-            'album': album,
-            'album_artist': album_artist,
-            'release_year': release_year,
         }
 
 
@@ -257,6 +233,5 @@ class BandcampAlbumIE(InfoExtractor):
             'uploader_id': uploader_id,
             'id': playlist_id,
             'title': title,
-            'album': title,
             'entries': entries,
-        }
+}

From 8edb8bc4a49ce1c66d422ef99c56c76998c3c4da Mon Sep 17 00:00:00 2001
From: gkoelln <gkoelln7@gmail.com>
Date: Fri, 27 Jan 2017 15:39:46 -0600
Subject: [PATCH 10/11] Trying to eliminate this file from pull request

---
 youtube_dl/extractor/bandcamp.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py
index 045ea6f6f..987238738 100644
--- a/youtube_dl/extractor/bandcamp.py
+++ b/youtube_dl/extractor/bandcamp.py
@@ -234,4 +234,4 @@ class BandcampAlbumIE(InfoExtractor):
             'id': playlist_id,
             'title': title,
             'entries': entries,
-}
+    }

From 227907a5d75eab4ef0a5f701250812bafaeb260d Mon Sep 17 00:00:00 2001
From: gkoelln <gkoelln7@gmail.com>
Date: Fri, 27 Jan 2017 21:38:27 -0600
Subject: [PATCH 11/11] Revert "[bandcamp] Fix free downloads extraction and
 extract all formats (closes #11067)"

This reverts commit 0aacd2deb1075e0d4d4b8b23b9a65b3967a1d658.
---
 youtube_dl/extractor/bandcamp.py | 86 +++++++++-----------------------
 1 file changed, 24 insertions(+), 62 deletions(-)

diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py
index 987238738..973d4bb80 100644
--- a/youtube_dl/extractor/bandcamp.py
+++ b/youtube_dl/extractor/bandcamp.py
@@ -1,9 +1,7 @@
 from __future__ import unicode_literals
 
 import json
-import random
 import re
-import time
 
 from .common import InfoExtractor
 from ..compat import (
@@ -14,9 +12,6 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     int_or_none,
-    parse_filesize,
-    unescapeHTML,
-    update_url_query,
 )
 
 
@@ -86,68 +81,35 @@ class BandcampIE(InfoExtractor):
             r'(?ms)var TralbumData = .*?[{,]\s*id: (?P<id>\d+),?$',
             webpage, 'video id')
 
-        download_webpage = self._download_webpage(
-            download_link, video_id, 'Downloading free downloads page')
-
-        blob = self._parse_json(
-            self._search_regex(
-                r'data-blob=(["\'])(?P<blob>{.+?})\1', download_webpage,
-                'blob', group='blob'),
-            video_id, transform_source=unescapeHTML)
-
-        info = blob['digital_items'][0]
-
-        downloads = info['downloads']
-        track = info['title']
-
-        artist = info.get('artist')
-        title = '%s - %s' % (artist, track) if artist else track
-
-        download_formats = {}
-        for f in blob['download_formats']:
-            name, ext = f.get('name'), f.get('file_extension')
-            if all(isinstance(x, compat_str) for x in (name, ext)):
-                download_formats[name] = ext.strip('.')
-
-        formats = []
-        for format_id, f in downloads.items():
-            format_url = f.get('url')
-            if not format_url:
-                continue
-            # Stat URL generation algorithm is reverse engineered from
-            # download_*_bundle_*.js
-            stat_url = update_url_query(
-                format_url.replace('/download/', '/statdownload/'), {
-                    '.rand': int(time.time() * 1000 * random.random()),
-                })
-            format_id = f.get('encoding_name') or format_id
-            stat = self._download_json(
-                stat_url, video_id, 'Downloading %s JSON' % format_id,
-                transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1],
-                fatal=False)
-            if not stat:
-                continue
-            retry_url = stat.get('retry_url')
-            if not isinstance(retry_url, compat_str):
-                continue
-            formats.append({
-                'url': self._proto_relative_url(retry_url, 'http:'),
-                'ext': download_formats.get(format_id),
-                'format_id': format_id,
-                'format_note': f.get('description'),
-                'filesize': parse_filesize(f.get('size_mb')),
-                'vcodec': 'none',
-            })
-        self._sort_formats(formats)
+        download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page')
+        # We get the dictionary of the track from some javascript code
+        all_info = self._parse_json(self._search_regex(
+            r'(?sm)items: (.*?),$', download_webpage, 'items'), video_id)
+        info = all_info[0]
+        # We pick mp3-320 for now, until format selection can be easily implemented.
+        mp3_info = info['downloads']['mp3-320']
+        # If we try to use this url it says the link has expired
+        initial_url = mp3_info['url']
+        m_url = re.match(
+            r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$',
+            initial_url)
+        # We build the url we will use to get the final track url
+        # This url is build in Bandcamp in the script download_bunde_*.js
+        request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), video_id, m_url.group('ts'))
+        final_url_webpage = self._download_webpage(request_url, video_id, 'Requesting download url')
+        # If we could correctly generate the .rand field the url would be
+        # in the "download_url" key
+        final_url = self._proto_relative_url(self._search_regex(
+            r'"retry_url":"(.+?)"', final_url_webpage, 'final video URL'), 'http:')
 
         return {
             'id': video_id,
-            'title': title,
+            'title': info['title'],
+            'ext': 'mp3',
+            'vcodec': 'none',
+            'url': final_url,
             'thumbnail': info.get('thumb_url'),
             'uploader': info.get('artist'),
-            'artist': artist,
-            'track': track,
-            'formats': formats,
         }