From 6766d7d7384f5ff694dd2eac9ab460b59ff43d2f Mon Sep 17 00:00:00 2001
From: Andrew Udvare <audvare@gmail.com>
Date: Tue, 20 Mar 2018 23:52:46 -0400
Subject: [PATCH 01/13] [cheeyvideosnet] Add new extractor

---
 youtube_dl/extractor/cheekyvideosnet.py | 41 +++++++++++++++++++++++++
 1 file changed, 41 insertions(+)
 create mode 100644 youtube_dl/extractor/cheekyvideosnet.py

diff --git a/youtube_dl/extractor/cheekyvideosnet.py b/youtube_dl/extractor/cheekyvideosnet.py
new file mode 100644
index 000000000..cf6be2905
--- /dev/null
+++ b/youtube_dl/extractor/cheekyvideosnet.py
@@ -0,0 +1,41 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class CheekyVideosIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?cheekyvideos\.net/(?P<id>.*)\.html?$'
+    _TEST = {
+        'url': 'https://yourextractor.com/watch/42',
+        'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)',
+        'info_dict': {
+            'id': '42',
+            'ext': 'mp4',
+            'title': 'Video title goes here',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            # TODO more properties, either as:
+            # * A value
+            # * MD5 checksum; start the string with md5:
+            # * A regular expression; start the string with re:
+            # * Any Python type (for example int or float)
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
+        video_url = self._html_search_regex(r'<video[^>]+.src="(videos/[^"]+)"', webpage, 'url')
+        uploader = video_id.split('/')[0]
+        video_id = video_id.split('/')[1]
+        url = 'https://cheekyvideos.net/%s/%s' % (uploader, video_url)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': self._html_search_meta('description', webpage, display_name='description'),
+            'uploader': uploader,
+            'url': url,
+        }

From 9e8a97c93c35d042db1084a40ddded421f57c9f3 Mon Sep 17 00:00:00 2001
From: Andrew Udvare <audvare@gmail.com>
Date: Tue, 20 Mar 2018 23:53:03 -0400
Subject: [PATCH 02/13] [pewtube] Add new extractor (may not be complete)

---
 youtube_dl/extractor/pewtube.py | 88 +++++++++++++++++++++++++++++++++
 1 file changed, 88 insertions(+)
 create mode 100644 youtube_dl/extractor/pewtube.py

diff --git a/youtube_dl/extractor/pewtube.py b/youtube_dl/extractor/pewtube.py
new file mode 100644
index 000000000..7f683f841
--- /dev/null
+++ b/youtube_dl/extractor/pewtube.py
@@ -0,0 +1,88 @@
+# coding: utf-8
+from __future__ import unicode_literals
+from collections import OrderedDict
+from datetime import datetime
+import re
+import subprocess as sp
+import time
+
+from .common import InfoExtractor
+from ..utils import CloudFlareSimpleJSChallengeMixin, int_or_none
+
+
+class PewTubeIE(InfoExtractor, CloudFlareSimpleJSChallengeMixin):
+    _VALID_URL = r'https?://(?:www\.)?pew\.tube/user/[^/]+/(?P<id>[^/]+)'
+    _TEST = {
+        'url': 'https://pew.tube/user/MrBond/4jLJf06',
+        'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)',
+        'info_dict': {
+            'id': '4jLJf06',
+            'ext': 'mp4',
+            'title': 'Mr. Bond - Good Old Nationalist',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            # TODO more properties, either as:
+            # * A value
+            # * MD5 checksum; start the string with md5:
+            # * A regular expression; start the string with re:
+            # * Any Python type (for example int or float)
+        }
+    }
+
+    def set_downloader(self, downloader):
+        self._downloader = downloader
+        if downloader:
+            class Handle503:
+                def http_error_503(self, request, response, code, msg, hdrs):
+                    return response
+            self._downloader._opener.handle_error['http'][503] = [Handle503()]
+
+    def _real_extract(self, url):
+        self._do_cloudflare_challenge('pew.tube', url, secure=True)
+
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(r'<h2 .*upload\-title\-value[^>]+>([^<]+)</h2>', webpage, 'title')
+        thumbnail = self._html_search_regex(r'<video .*poster="(https[^"]+)"', webpage, 'thumbnail', fatal=False)
+        video_url = self._html_search_regex(r'<(?:audio|video)[^>]+>.*<source.*src="([^"]+)".*</(?:audio|video)>', webpage, 'video URL')
+        uploader = self._html_search_regex(r'<h3 .*class="uploader\-name"[^>]+>by \&nbsp;?<a[^>]+>([^<]+)</a>', webpage, 'uploader')
+        description = self._html_search_meta('description', webpage, 'description')
+        view_count = self._html_search_regex(r'<h3(?:[^>]+)?>(\d+)(?:\s+)[vV]iews</h3>', webpage, 'view count')
+
+        like_count = 0
+        for like_class in ('like', 'laugh', 'love',):
+            like_count += int(self._html_search_regex(r'<p class="{}">(\d+)</p>'.format(like_class), webpage, '{} count'))
+
+        dislike_count = 0
+        for dislike_class in ('dislike', 'sad', 'discount',):
+            dislike_count += int(self._html_search_regex(r'<p class="{}">(\d+)</p>'.format(like_class), webpage, '{} count'))
+
+        like_count = None if not like_count else like_count
+        dislike_count = None if not dislike_count else dislike_count
+
+        if not thumbnail:
+            thumbnail = self._og_search_thumbnail(webpage)
+        if not description:
+            description = self._og_search_description(webpage)
+
+        # TODO Parse fuzzy upload date
+        #upload_date_s = self._html_search_regex(r'<h4>Uploaded ([^<]+)</h4>', webpage, 'upload date')
+        #today = datetime.today()
+        #upload_date_s = re.sub(r'(?:\s+)ago$', '', upload_date_s)
+        #n, unit = re.search('^(?P<n>\d+)\s(?:\s+)?(?P<unit>.*)').groups()
+        #unit = unit.lower()
+        #if unit == 'month':
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'uploader': uploader,
+            'creator': uploader,
+            'uploader_url': '/'.join(url.split('/')[:-1]),
+            'thumbnail': thumbnail,
+            'view_count': int_or_none(view_count),
+            'like_count': like_count,
+            'dislike_count': dislike_count,
+            'url': video_url,
+        }

From 979638891b9dbcc4e0876ecd7142fe0c055b3a72 Mon Sep 17 00:00:00 2001
From: Andrew Udvare <audvare@gmail.com>
Date: Tue, 20 Mar 2018 23:53:53 -0400
Subject: [PATCH 03/13] Ignore KDevelop project file

---
 .gitignore | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.gitignore b/.gitignore
index fbf7cecb2..bfbff4faf 100644
--- a/.gitignore
+++ b/.gitignore
@@ -45,5 +45,6 @@ youtube-dl.zsh
 # IntelliJ related files
 .idea
 *.iml
+*.kdev4
 
 tmp/

From 86f7fcbe6975e97ca9b3c40c624a6df15e730556 Mon Sep 17 00:00:00 2001
From: Andrew Udvare <audvare@gmail.com>
Date: Tue, 20 Mar 2018 23:54:13 -0400
Subject: [PATCH 04/13] Numeric parser (for jsinterp)

---
 parse-numeric.py | 116 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 116 insertions(+)
 create mode 100644 parse-numeric.py

diff --git a/parse-numeric.py b/parse-numeric.py
new file mode 100644
index 000000000..6c41f8c3d
--- /dev/null
+++ b/parse-numeric.py
@@ -0,0 +1,116 @@
+from __future__ import print_function
+import math
+import re
+
+regex = re.compile(r'''(?:\s+)? # StrNumericLiteral.StrWhiteSpace (optional)
+            ( # StringNumericLitral.StrDecimalLiteral
+                (?P<inf_sign>[\+\-])? # optional sign
+                (?P<inf>Infinity)|
+                [\+\-]?(?P<nan>NaN)|  # not documented, but Node returns NaN
+                [\+\-]?(?:  # DecimalDigits . DecimalDigits(opt) ExponentPart(opt)
+                    (?:\d+)? # DecimalDigits
+                    (?:\.)
+                    (?:\d+)? # DecimalDigits
+                    (?:[eE] # ExponentPart.ExponentIndicator
+                        [\+\=]?  # optional sign
+                        (?:\d+)
+                    )?
+                )|
+                0(?P<binary>[bB])(?P<binary_number>[01]+)|
+                0(?P<octal>[oO])(?P<octal_number>[01234567]+)|
+                0(?P<hex>[xX])(?P<hex_number>[0-9a-fA-F]+)
+            )(?:\s+)?$''', re.X)
+
+
+def getnan():
+    try:
+        return math.nan
+    except AttributeError:
+        pass
+    return float('nan')
+
+
+def getinf(mult=1):
+    try:
+        ret = math.inf
+    except AttributeError:
+        ret = float('inf')
+    return mult * ret
+
+
+def can_be_int(inp, out):
+    return str(out)[-2:] == '.0' and ('.0' not in inp and not inp.endswith('.'))
+
+
+def conditional_int(inp):
+    # Values with leading zeros like 01.0 and 01. should fail
+    if len(inp) > 1 and inp[0] == '0':
+        raise SyntaxError('unexpected number; given "{}"'.format(inp))
+    out = float(inp)
+    return int(str(out)[:-2], 10) if can_be_int(inp, out) else out
+
+
+def parse_numeric(x):
+    m = re.match(regex, x)
+    if not m:
+        raise SyntaxError('invalid nor unexpected token; given "{}"'.format(x))
+
+    ret = m.group(0).strip()
+    groups = m.groupdict()
+
+    if groups['inf']:
+        sign = -1 if groups['inf_sign'] == '-' else 1
+        ret = getinf(sign)
+    elif groups['nan']:
+        ret = getnan()
+    else:
+        base = key = None
+        if groups['binary']:
+            base = 2
+            key = 'binary_number'
+        elif groups['octal']:
+            base = 8
+            key = 'octal_number'
+        elif groups['hex']:
+            base = 16
+            key = 'hex_number'
+        if key and base:
+            ret = int(groups[key], base)
+        else:
+            try:
+                ret = conditional_int(ret)
+            except ValueError as e:
+                raise SyntaxError('invalid or unexpected token: given "{}"'.format(x))
+    print('{} -> {}'.format(x, ret))
+    return ret
+
+parse_numeric('.1')
+parse_numeric('1.')
+parse_numeric('Infinity')
+parse_numeric('-Infinity')
+parse_numeric('+Infinity')
+parse_numeric('NaN')
+parse_numeric('-NaN')
+parse_numeric('+NaN')
+try:
+    parse_numeric('01.0')
+except SyntaxError as e:
+    print('01.0 -> {}'.format(e))
+try:
+    parse_numeric('01.')
+except SyntaxError as e:
+    print('01. -> {}'.format(e))
+parse_numeric('1.0')
+parse_numeric('1.1')
+parse_numeric('1.e5')
+parse_numeric('1.E5')
+parse_numeric('1.1e5')
+parse_numeric('1.1E6')
+parse_numeric('-1.1E6')
+parse_numeric('+1.1')
+parse_numeric('0b101')
+parse_numeric('0B101')
+parse_numeric('0o755')
+parse_numeric('0O755')
+parse_numeric('0xaf')
+parse_numeric('0XDEADBEEF9')

From d56e384309121b3b1b7f0276d3003c770a6b3ae9 Mon Sep 17 00:00:00 2001
From: Andrew Udvare <audvare@gmail.com>
Date: Sat, 28 Apr 2018 02:45:21 -0400
Subject: [PATCH 05/13] Fix PewTube extractor

---
 youtube_dl/extractor/extractors.py |  5 ++-
 youtube_dl/extractor/pewtube.py    | 53 +++++++++++++++++-------------
 2 files changed, 34 insertions(+), 24 deletions(-)

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 6fb65e4fe..f4c64642d 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -1332,7 +1332,7 @@ from .webofstories import (
     WebOfStoriesPlaylistIE,
 )
 from .weibo import (
-    WeiboIE, 
+    WeiboIE,
     WeiboMobileIE
 )
 from .weiqitv import WeiqiTVIE
@@ -1420,3 +1420,6 @@ from .zapiks import ZapiksIE
 from .zaq1 import Zaq1IE
 from .zdf import ZDFIE, ZDFChannelIE
 from .zingmp3 import ZingMp3IE
+
+from .cheekyvideosnet import CheekyVideosIE
+from .pewtube import PewTubeIE
diff --git a/youtube_dl/extractor/pewtube.py b/youtube_dl/extractor/pewtube.py
index 7f683f841..e017fc182 100644
--- a/youtube_dl/extractor/pewtube.py
+++ b/youtube_dl/extractor/pewtube.py
@@ -1,17 +1,17 @@
 # coding: utf-8
 from __future__ import unicode_literals
 from collections import OrderedDict
-from datetime import datetime
+from datetime import datetime, timedelta
 import re
 import subprocess as sp
 import time
 
 from .common import InfoExtractor
-from ..utils import CloudFlareSimpleJSChallengeMixin, int_or_none
+from ..utils import int_or_none
 
 
-class PewTubeIE(InfoExtractor, CloudFlareSimpleJSChallengeMixin):
-    _VALID_URL = r'https?://(?:www\.)?pew\.tube/user/[^/]+/(?P<id>[^/]+)'
+class PewTubeIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?pewtube\.com/user/[^/]+/(?P<id>[^/]+)'
     _TEST = {
         'url': 'https://pew.tube/user/MrBond/4jLJf06',
         'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)',
@@ -28,24 +28,18 @@ class PewTubeIE(InfoExtractor, CloudFlareSimpleJSChallengeMixin):
         }
     }
 
-    def set_downloader(self, downloader):
-        self._downloader = downloader
-        if downloader:
-            class Handle503:
-                def http_error_503(self, request, response, code, msg, hdrs):
-                    return response
-            self._downloader._opener.handle_error['http'][503] = [Handle503()]
-
     def _real_extract(self, url):
-        self._do_cloudflare_challenge('pew.tube', url, secure=True)
-
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(url, video_id, tries=5, timeout=15)
 
         title = self._html_search_regex(r'<h2 .*upload\-title\-value[^>]+>([^<]+)</h2>', webpage, 'title')
         thumbnail = self._html_search_regex(r'<video .*poster="(https[^"]+)"', webpage, 'thumbnail', fatal=False)
+        if not thumbnail:
+            thumbnail = self._og_search_thumbnail(webpage)
         video_url = self._html_search_regex(r'<(?:audio|video)[^>]+>.*<source.*src="([^"]+)".*</(?:audio|video)>', webpage, 'video URL')
-        uploader = self._html_search_regex(r'<h3 .*class="uploader\-name"[^>]+>by \&nbsp;?<a[^>]+>([^<]+)</a>', webpage, 'uploader')
+        if not video_url:
+            video_url = self._og_search_video_url(webpage)
+        uploader = self._html_search_regex(r'<h3.*class="uploader-name"[^>]+>.*<a href="/user[^>]+>([^<]+)', webpage, 'uploader')
         description = self._html_search_meta('description', webpage, 'description')
         view_count = self._html_search_regex(r'<h3(?:[^>]+)?>(\d+)(?:\s+)[vV]iews</h3>', webpage, 'view count')
 
@@ -65,13 +59,25 @@ class PewTubeIE(InfoExtractor, CloudFlareSimpleJSChallengeMixin):
         if not description:
             description = self._og_search_description(webpage)
 
-        # TODO Parse fuzzy upload date
-        #upload_date_s = self._html_search_regex(r'<h4>Uploaded ([^<]+)</h4>', webpage, 'upload date')
-        #today = datetime.today()
-        #upload_date_s = re.sub(r'(?:\s+)ago$', '', upload_date_s)
-        #n, unit = re.search('^(?P<n>\d+)\s(?:\s+)?(?P<unit>.*)').groups()
-        #unit = unit.lower()
-        #if unit == 'month':
+        upload_date_s = ou = self._html_search_regex(r'<h4>Uploaded ([^<]+)</h4>', webpage, 'upload date')
+        today = datetime.today()
+        upload_date_s = re.sub(r'(?:\s+)ago\s+\&nbsp;?$', '', upload_date_s)
+        n, unit = re.search('^(?P<n>\d+)\s(?:\s+)?(?P<unit>.*)', upload_date_s).groups()
+        n = int(n)
+        unit = unit.lower()
+        total_seconds = 0
+        if not unit.endswith('s'):
+            unit += 's'
+        if unit == 'months':
+            total_seconds = n * 86400 * 30
+        elif unit == 'weeks':
+            total_seconds = n * 86400 * 7
+        elif unit in ('days', 'hours', 'minutes', 'seconds'):
+            if unit == 'days' and n >= 1:
+                total_seconds = n * 86400
+        else:
+            raise ValueError('Unhandled string: "{}" from "{}"'.format(unit, ou))
+        upload_date = (today - timedelta(seconds=total_seconds)).strftime('%Y%m%d')
 
         return {
             'id': video_id,
@@ -84,5 +90,6 @@ class PewTubeIE(InfoExtractor, CloudFlareSimpleJSChallengeMixin):
             'view_count': int_or_none(view_count),
             'like_count': like_count,
             'dislike_count': dislike_count,
+            'upload_date': upload_date,
             'url': video_url,
         }

From 60100061f5473774a9b3ed752a8364f901fc2695 Mon Sep 17 00:00:00 2001
From: Andrew Udvare <audvare@gmail.com>
Date: Sat, 28 Apr 2018 03:11:57 -0400
Subject: [PATCH 06/13] [PewTube] Adjust upload date calculation

---
 youtube_dl/extractor/pewtube.py | 29 ++++++++++++++++-------------
 1 file changed, 16 insertions(+), 13 deletions(-)

diff --git a/youtube_dl/extractor/pewtube.py b/youtube_dl/extractor/pewtube.py
index e017fc182..e429da21a 100644
--- a/youtube_dl/extractor/pewtube.py
+++ b/youtube_dl/extractor/pewtube.py
@@ -7,7 +7,7 @@ import subprocess as sp
 import time
 
 from .common import InfoExtractor
-from ..utils import int_or_none
+from ..utils import compat_str, int_or_none
 
 
 class PewTubeIE(InfoExtractor):
@@ -62,22 +62,25 @@ class PewTubeIE(InfoExtractor):
         upload_date_s = ou = self._html_search_regex(r'<h4>Uploaded ([^<]+)</h4>', webpage, 'upload date')
         today = datetime.today()
         upload_date_s = re.sub(r'(?:\s+)ago\s+\&nbsp;?$', '', upload_date_s)
-        n, unit = re.search('^(?P<n>\d+)\s(?:\s+)?(?P<unit>.*)', upload_date_s).groups()
-        n = int(n)
-        unit = unit.lower()
+        n, unit = re.search('^(?P<n>(?:\d+|a))\s(?:\s+)?(?P<unit>.*)', upload_date_s).groups()
+        if n == 'a':
+            n = 1
+        else:
+            n = int(n)
+        unit = unit.lower().encode('utf-8')
         total_seconds = 0
         if not unit.endswith('s'):
             unit += 's'
         if unit == 'months':
-            total_seconds = n * 86400 * 30
-        elif unit == 'weeks':
-            total_seconds = n * 86400 * 7
-        elif unit in ('days', 'hours', 'minutes', 'seconds'):
-            if unit == 'days' and n >= 1:
-                total_seconds = n * 86400
-        else:
-            raise ValueError('Unhandled string: "{}" from "{}"'.format(unit, ou))
-        upload_date = (today - timedelta(seconds=total_seconds)).strftime('%Y%m%d')
+            unit = 'weeks'
+            n *= 4
+        elif unit == 'years':
+            unit = 'weeks'
+            n *= 52
+        kwargs = dict()
+        kwargs[unit] = n
+        td = timedelta(**kwargs)
+        upload_date = (today - td).strftime('%Y%m%d')
 
         return {
             'id': video_id,

From 66086f7950a504433aee2ce35da85ef4660c9b8a Mon Sep 17 00:00:00 2001
From: Andrew Udvare <audvare@gmail.com>
Date: Sun, 10 Jun 2018 02:20:26 -0400
Subject: [PATCH 07/13] Fix for CCTV older videos

---
 youtube_dl/extractor/cctv.py | 33 +++++++++++++++++++++++++++++++--
 1 file changed, 31 insertions(+), 2 deletions(-)

diff --git a/youtube_dl/extractor/cctv.py b/youtube_dl/extractor/cctv.py
index c76f361c6..757f1a885 100644
--- a/youtube_dl/extractor/cctv.py
+++ b/youtube_dl/extractor/cctv.py
@@ -4,9 +4,13 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_str
+from ..compat import (
+    compat_str,
+    compat_urlparse,
+)
 from ..utils import (
     float_or_none,
+    int_or_none,
     try_get,
     unified_timestamp,
 )
@@ -132,6 +136,7 @@ class CCTVIE(InfoExtractor):
         video_id = self._search_regex(
             [r'var\s+guid\s*=\s*["\']([\da-fA-F]+)',
              r'videoCenterId["\']\s*,\s*["\']([\da-fA-F]+)',
+             r'video(?:Center)?Id=([\da-f]+)',
              r'changePlayer\s*\(\s*["\']([\da-fA-F]+)',
              r'load[Vv]ideo\s*\(\s*["\']([\da-fA-F]+)',
              r'var\s+initMyAray\s*=\s*["\']([\da-fA-F]+)',
@@ -146,7 +151,31 @@ class CCTVIE(InfoExtractor):
                 'idl': 32,
                 'idlr': 32,
                 'modifyed': 'false',
-            })
+            }, fatal=False)
+        if data.get('status') == 'not_exist' or not data:
+            p = compat_urlparse.urlsplit(url, scheme='http')
+            path = self._search_regex(r'filePath=(/[^\&"]+)', webpage, 'filePath')
+            beg = video_id[0:8]
+            ending = video_id[8:]
+            url = '%s://%s%s%s/%s.txt' % (p.scheme, p.netloc, path, beg, ending)
+            data = self._download_webpage(url, ending, 'Downloading JSON metadata')
+            data = re.sub(r'(?:\s+)?<\!\-+[^\-]+\-+>.*', '', data)
+            data = self._parse_json(data, video_id)
+            entries = []
+            title = data.get('title')
+            for i, chapter in enumerate(data.get('chapters', [])):
+                url = chapter.get('url')
+                if title:
+                    ctitle = '%s (Chapter %02d)' % (title, i + 1,)
+                else:
+                    ctitle = 'Chapter %02d' % (i + 1,)
+                if url:
+                    entries.append(dict(id='%s_%02d' % (video_id, i,),
+                                        thumbnail=data.get('imagePath'),
+                                        title=ctitle,
+                                        duration=int_or_none(chapter.get('duration')),
+                                        url=url))
+            return self.playlist_result(entries, playlist_id=video_id, playlist_title=data.get('title'))
 
         title = data['title']
 

From b8bd2a22cb354e29a17cae26e631ac6b976cb7c8 Mon Sep 17 00:00:00 2001
From: Andrew Udvare <audvare@gmail.com>
Date: Sun, 10 Jun 2018 11:57:40 -0400
Subject: [PATCH 08/13] Test; fetch upload date and timestamp

---
 youtube_dl/extractor/cctv.py | 28 ++++++++++++++++++++++++++--
 1 file changed, 26 insertions(+), 2 deletions(-)

diff --git a/youtube_dl/extractor/cctv.py b/youtube_dl/extractor/cctv.py
index 757f1a885..00db6cff1 100644
--- a/youtube_dl/extractor/cctv.py
+++ b/youtube_dl/extractor/cctv.py
@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+from calendar import timegm
+from datetime import datetime
 import re
 
 from .common import InfoExtractor
@@ -22,7 +24,6 @@ class CCTVIE(InfoExtractor):
     _TESTS = [{
         # fo.addVariable("videoCenterId","id")
         'url': 'http://sports.cntv.cn/2016/02/12/ARTIaBRxv4rTT1yWf1frW2wi160212.shtml',
-        'md5': 'd61ec00a493e09da810bf406a078f691',
         'info_dict': {
             'id': '5ecdbeab623f4973b40ff25f18b174e8',
             'ext': 'mp4',
@@ -112,6 +113,17 @@ class CCTVIE(InfoExtractor):
             'skip_download': True,
         },
         'expected_warnings': ['Failed to download m3u8 information'],
+    }, {
+        # older multi-part streams, non-HLS
+        'url': 'http://english.cntv.cn/program/learnchinese/20110325/103360.shtml',
+        'info_dict': {
+            'id': '20110325100557_00',
+            'ext': 'mp4',
+            'title': 'Learn to Speak Chinese Edition 24-2011 (Chapter 01)',
+            'duration': 295,
+            'timestamp': 1301053440,
+            'upload_date': '20110325',
+        },
     }, {
         'url': 'http://ent.cntv.cn/2016/01/18/ARTIjprSSJH8DryTVr5Bx8Wb160118.shtml',
         'only_matching': True,
@@ -163,6 +175,12 @@ class CCTVIE(InfoExtractor):
             data = self._parse_json(data, video_id)
             entries = []
             title = data.get('title')
+            upload_date = self._search_regex(
+                '<em>(?:\s+)?(\d{2}\-\d{2}\-\d{4}\s+\d{2}\:\d{2})[^<]+',
+                webpage, 'upload date', fatal=False).strip()
+            upload_date = re.sub(r'\s+', ' ', upload_date)
+            udt = datetime.strptime(upload_date, '%m-%d-%Y %H:%M')
+
             for i, chapter in enumerate(data.get('chapters', [])):
                 url = chapter.get('url')
                 if title:
@@ -170,12 +188,18 @@ class CCTVIE(InfoExtractor):
                 else:
                     ctitle = 'Chapter %02d' % (i + 1,)
                 if url:
+                    if not url.startswith('http'):
+                        url = re.sub(r'^[^\:]+', 'http', url)
                     entries.append(dict(id='%s_%02d' % (video_id, i,),
                                         thumbnail=data.get('imagePath'),
                                         title=ctitle,
                                         duration=int_or_none(chapter.get('duration')),
+                                        upload_date=udt.strftime('%Y%m%d'),
+                                        timestamp=timegm(udt.timetuple()),
                                         url=url))
-            return self.playlist_result(entries, playlist_id=video_id, playlist_title=data.get('title'))
+            return self.playlist_result(entries,
+                                        playlist_id=video_id,
+                                        playlist_title=title)
 
         title = data['title']
 

From 64828b8fe83fa615a187ddf9c5577ff69efc59ac Mon Sep 17 00:00:00 2001
From: Andrew Udvare <audvare@gmail.com>
Date: Sun, 10 Jun 2018 12:44:52 -0400
Subject: [PATCH 09/13] More metadata

---
 youtube_dl/extractor/cctv.py | 27 +++++++++++++++++----------
 1 file changed, 17 insertions(+), 10 deletions(-)

diff --git a/youtube_dl/extractor/cctv.py b/youtube_dl/extractor/cctv.py
index 00db6cff1..7c7934a23 100644
--- a/youtube_dl/extractor/cctv.py
+++ b/youtube_dl/extractor/cctv.py
@@ -117,12 +117,14 @@ class CCTVIE(InfoExtractor):
         # older multi-part streams, non-HLS
         'url': 'http://english.cntv.cn/program/learnchinese/20110325/103360.shtml',
         'info_dict': {
-            'id': '20110325100557_00',
+            'id': '20110325100557',
             'ext': 'mp4',
-            'title': 'Learn to Speak Chinese Edition 24-2011 (Chapter 01)',
-            'duration': 295,
+            'title': 're:^Learn to Speak Chinese Edition 24-2011',
             'timestamp': 1301053440,
             'upload_date': '20110325',
+            'uploader': 'Beauty',
+            'creator': 'CNTV',
+            'description': 'Mike：兰兰，你在哪儿啊？\nMike：Lan Lan，where are you?\n兰兰：噢，是麦克呀。我刚才去游泳了，正打算回家呢。麦克，你有什么事儿吗？',
         },
     }, {
         'url': 'http://ent.cntv.cn/2016/01/18/ARTIjprSSJH8DryTVr5Bx8Wb160118.shtml',
@@ -174,27 +176,32 @@ class CCTVIE(InfoExtractor):
             data = re.sub(r'(?:\s+)?<\!\-+[^\-]+\-+>.*', '', data)
             data = self._parse_json(data, video_id)
             entries = []
-            title = data.get('title')
+            title = data['title']
             upload_date = self._search_regex(
                 '<em>(?:\s+)?(\d{2}\-\d{2}\-\d{4}\s+\d{2}\:\d{2})[^<]+',
                 webpage, 'upload date', fatal=False).strip()
             upload_date = re.sub(r'\s+', ' ', upload_date)
             udt = datetime.strptime(upload_date, '%m-%d-%Y %H:%M')
+            desc = self._html_search_meta('description', webpage, 'description')
+            desc = desc.replace('\r', '\n').replace('\n ', '\n')
+            creator = self._html_search_regex(r'<b>(?:\s+)?Source\:(?:\s+)?</b>(?:\s+)?([^<]+)',
+                                              webpage, 'source')
+            editor = self._html_search_regex(r'<b>(?:\s+)?Editor\:</b>(?:\s+)?([^<\|]+)',
+                                             webpage, 'editor').strip()
 
             for i, chapter in enumerate(data.get('chapters', [])):
                 url = chapter.get('url')
-                if title:
-                    ctitle = '%s (Chapter %02d)' % (title, i + 1,)
-                else:
-                    ctitle = 'Chapter %02d' % (i + 1,)
                 if url:
                     if not url.startswith('http'):
                         url = re.sub(r'^[^\:]+', 'http', url)
-                    entries.append(dict(id='%s_%02d' % (video_id, i,),
+                    entries.append(dict(id=video_id,
                                         thumbnail=data.get('imagePath'),
-                                        title=ctitle,
+                                        title='%s - %02d' % (title, i + 1,),
                                         duration=int_or_none(chapter.get('duration')),
                                         upload_date=udt.strftime('%Y%m%d'),
+                                        description=desc,
+                                        uploader=editor,
+                                        creator=creator,
                                         timestamp=timegm(udt.timetuple()),
                                         url=url))
             return self.playlist_result(entries,

From 8d245cf42f407fdb49b5b514f8698b1421f0c975 Mon Sep 17 00:00:00 2001
From: Andrew Udvare <audvare@gmail.com>
Date: Sat, 23 Jun 2018 00:37:59 -0400
Subject: [PATCH 10/13] [archiveorg] Some thumbnail URLs are relative

---
 youtube_dl/extractor/archiveorg.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/youtube_dl/extractor/archiveorg.py b/youtube_dl/extractor/archiveorg.py
index c79c58e82..d24cf8686 100644
--- a/youtube_dl/extractor/archiveorg.py
+++ b/youtube_dl/extractor/archiveorg.py
@@ -62,4 +62,8 @@ class ArchiveOrgIE(InfoExtractor):
                 'uploader': get_optional(metadata, 'creator'),
                 'upload_date': unified_strdate(get_optional(metadata, 'date')),
             })
+        if info.get('thumbnail', '').startswith('/'):
+            info.update({
+                'thumbnail': 'https://archive.org%s' % info.get('thumbnail')
+            })
         return info

From a8aa503d9988c7b2de0e936c7952f7e7e660ca7d Mon Sep 17 00:00:00 2001
From: Andrew Udvare <audvare@gmail.com>
Date: Sat, 30 Jun 2018 08:18:11 -0400
Subject: [PATCH 11/13] Remove old file

---
 parse-numeric.py | 116 -----------------------------------------------
 1 file changed, 116 deletions(-)
 delete mode 100644 parse-numeric.py

diff --git a/parse-numeric.py b/parse-numeric.py
deleted file mode 100644
index 6c41f8c3d..000000000
--- a/parse-numeric.py
+++ /dev/null
@@ -1,116 +0,0 @@
-from __future__ import print_function
-import math
-import re
-
-regex = re.compile(r'''(?:\s+)? # StrNumericLiteral.StrWhiteSpace (optional)
-            ( # StringNumericLitral.StrDecimalLiteral
-                (?P<inf_sign>[\+\-])? # optional sign
-                (?P<inf>Infinity)|
-                [\+\-]?(?P<nan>NaN)|  # not documented, but Node returns NaN
-                [\+\-]?(?:  # DecimalDigits . DecimalDigits(opt) ExponentPart(opt)
-                    (?:\d+)? # DecimalDigits
-                    (?:\.)
-                    (?:\d+)? # DecimalDigits
-                    (?:[eE] # ExponentPart.ExponentIndicator
-                        [\+\=]?  # optional sign
-                        (?:\d+)
-                    )?
-                )|
-                0(?P<binary>[bB])(?P<binary_number>[01]+)|
-                0(?P<octal>[oO])(?P<octal_number>[01234567]+)|
-                0(?P<hex>[xX])(?P<hex_number>[0-9a-fA-F]+)
-            )(?:\s+)?$''', re.X)
-
-
-def getnan():
-    try:
-        return math.nan
-    except AttributeError:
-        pass
-    return float('nan')
-
-
-def getinf(mult=1):
-    try:
-        ret = math.inf
-    except AttributeError:
-        ret = float('inf')
-    return mult * ret
-
-
-def can_be_int(inp, out):
-    return str(out)[-2:] == '.0' and ('.0' not in inp and not inp.endswith('.'))
-
-
-def conditional_int(inp):
-    # Values with leading zeros like 01.0 and 01. should fail
-    if len(inp) > 1 and inp[0] == '0':
-        raise SyntaxError('unexpected number; given "{}"'.format(inp))
-    out = float(inp)
-    return int(str(out)[:-2], 10) if can_be_int(inp, out) else out
-
-
-def parse_numeric(x):
-    m = re.match(regex, x)
-    if not m:
-        raise SyntaxError('invalid nor unexpected token; given "{}"'.format(x))
-
-    ret = m.group(0).strip()
-    groups = m.groupdict()
-
-    if groups['inf']:
-        sign = -1 if groups['inf_sign'] == '-' else 1
-        ret = getinf(sign)
-    elif groups['nan']:
-        ret = getnan()
-    else:
-        base = key = None
-        if groups['binary']:
-            base = 2
-            key = 'binary_number'
-        elif groups['octal']:
-            base = 8
-            key = 'octal_number'
-        elif groups['hex']:
-            base = 16
-            key = 'hex_number'
-        if key and base:
-            ret = int(groups[key], base)
-        else:
-            try:
-                ret = conditional_int(ret)
-            except ValueError as e:
-                raise SyntaxError('invalid or unexpected token: given "{}"'.format(x))
-    print('{} -> {}'.format(x, ret))
-    return ret
-
-parse_numeric('.1')
-parse_numeric('1.')
-parse_numeric('Infinity')
-parse_numeric('-Infinity')
-parse_numeric('+Infinity')
-parse_numeric('NaN')
-parse_numeric('-NaN')
-parse_numeric('+NaN')
-try:
-    parse_numeric('01.0')
-except SyntaxError as e:
-    print('01.0 -> {}'.format(e))
-try:
-    parse_numeric('01.')
-except SyntaxError as e:
-    print('01. -> {}'.format(e))
-parse_numeric('1.0')
-parse_numeric('1.1')
-parse_numeric('1.e5')
-parse_numeric('1.E5')
-parse_numeric('1.1e5')
-parse_numeric('1.1E6')
-parse_numeric('-1.1E6')
-parse_numeric('+1.1')
-parse_numeric('0b101')
-parse_numeric('0B101')
-parse_numeric('0o755')
-parse_numeric('0O755')
-parse_numeric('0xaf')
-parse_numeric('0XDEADBEEF9')

From 1b02c9f96bab7be30bc90dfba54c5cb1e3d3db34 Mon Sep 17 00:00:00 2001
From: Andrew Udvare <audvare@gmail.com>
Date: Sat, 30 Jun 2018 08:18:32 -0400
Subject: [PATCH 12/13] Get description or None

---
 youtube_dl/extractor/cheekyvideosnet.py | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/youtube_dl/extractor/cheekyvideosnet.py b/youtube_dl/extractor/cheekyvideosnet.py
index cf6be2905..4dd33946a 100644
--- a/youtube_dl/extractor/cheekyvideosnet.py
+++ b/youtube_dl/extractor/cheekyvideosnet.py
@@ -14,11 +14,6 @@ class CheekyVideosIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Video title goes here',
             'thumbnail': r're:^https?://.*\.jpg$',
-            # TODO more properties, either as:
-            # * A value
-            # * MD5 checksum; start the string with md5:
-            # * A regular expression; start the string with re:
-            # * Any Python type (for example int or float)
         }
     }
 
@@ -35,7 +30,7 @@ class CheekyVideosIE(InfoExtractor):
         return {
             'id': video_id,
             'title': title,
-            'description': self._html_search_meta('description', webpage, display_name='description'),
+            'description': self._html_search_meta('description', webpage, default=None),
             'uploader': uploader,
             'url': url,
         }

From 713f2b4f1ae8a5a79e0de8bc95235ef209b6d88c Mon Sep 17 00:00:00 2001
From: Andrew Udvare <audvare@gmail.com>
Date: Thu, 16 Aug 2018 04:40:44 -0400
Subject: [PATCH 13/13] [cbslocal] Update access key and API key

---
 youtube_dl/extractor/anvato.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/youtube_dl/extractor/anvato.py b/youtube_dl/extractor/anvato.py
index f6a78eb5d..17a5bc321 100644
--- a/youtube_dl/extractor/anvato.py
+++ b/youtube_dl/extractor/anvato.py
@@ -116,7 +116,9 @@ class AnvatoIE(InfoExtractor):
         'anvato_scripps_app_ios_prod_409c41960c60b308db43c3cc1da79cab9f1c3d93': 'WPxj5GraLTkYCyj3M7RozLqIycjrXOEcDGFMIJPn',
         'EZqvRyKBJLrgpClDPDF8I7Xpdp40Vx73': '4OxGd2dEakylntVKjKF0UK9PDPYB6A9W',
         'M2v78QkpleXm9hPp9jUXI63x5vA6BogR': 'ka6K32k7ZALmpINkjJUGUo0OE42Md1BQ',
-        'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6_secure': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ'
+        'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6_secure': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ',
+        # CBS Local 2018-08-16
+        'DVzl9QRzox3ZZsP9bNu5Li3X7obQOnqP': '3hwbSuqqT690uxjNYBktSQpa5ZrpYYR0Iofx7NcJHyA',
     }
 
     _MCP_TO_ACCESS_KEY_TABLE = {