aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--.github/workflows/build.yml4
-rw-r--r--youtube_dlc/downloader/external.py29
-rw-r--r--youtube_dlc/extractor/extractors.py1
-rw-r--r--youtube_dlc/extractor/thisvid.py97
-rw-r--r--youtube_dlc/extractor/youtube.py7
-rw-r--r--youtube_dlc/extractor/zoom.py2
6 files changed, 123 insertions, 17 deletions
diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index 74b50ecca..4920a30b8 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -82,7 +82,7 @@ jobs:
- name: Set up Python
uses: actions/setup-python@v2
with:
- python-version: '3.x'
+ python-version: '3.8'
- name: Install Requirements
run: pip install pyinstaller
- name: Bump version
@@ -116,7 +116,7 @@ jobs:
- name: Set up Python 3.5.4 32-Bit
uses: actions/setup-python@v2
with:
- python-version: '3.5.4'
+ python-version: '3.4.4'
architecture: 'x86'
- name: Install Requirements for 32 Bit
run: pip install pyinstaller==3.5
diff --git a/youtube_dlc/downloader/external.py b/youtube_dlc/downloader/external.py
index c31f8910a..d2f8f271d 100644
--- a/youtube_dlc/downloader/external.py
+++ b/youtube_dlc/downloader/external.py
@@ -115,8 +115,10 @@ class CurlFD(ExternalFD):
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '--location', '-o', tmpfilename]
- for key, val in info_dict['http_headers'].items():
- cmd += ['--header', '%s: %s' % (key, val)]
+ if info_dict.get('http_headers') is not None:
+ for key, val in info_dict['http_headers'].items():
+ cmd += ['--header', '%s: %s' % (key, val)]
+
cmd += self._bool_option('--continue-at', 'continuedl', '-', '0')
cmd += self._valueless_option('--silent', 'noprogress')
cmd += self._valueless_option('--verbose', 'verbose')
@@ -150,8 +152,9 @@ class AxelFD(ExternalFD):
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '-o', tmpfilename]
- for key, val in info_dict['http_headers'].items():
- cmd += ['-H', '%s: %s' % (key, val)]
+ if info_dict.get('http_headers') is not None:
+ for key, val in info_dict['http_headers'].items():
+ cmd += ['-H', '%s: %s' % (key, val)]
cmd += self._configuration_args()
cmd += ['--', info_dict['url']]
return cmd
@@ -162,8 +165,9 @@ class WgetFD(ExternalFD):
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '-O', tmpfilename, '-nv', '--no-cookies']
- for key, val in info_dict['http_headers'].items():
- cmd += ['--header', '%s: %s' % (key, val)]
+ if info_dict.get('http_headers') is not None:
+ for key, val in info_dict['http_headers'].items():
+ cmd += ['--header', '%s: %s' % (key, val)]
cmd += self._option('--limit-rate', 'ratelimit')
retry = self._option('--tries', 'retries')
if len(retry) == 2:
@@ -189,8 +193,9 @@ class Aria2cFD(ExternalFD):
if dn:
cmd += ['--dir', dn]
cmd += ['--out', os.path.basename(tmpfilename)]
- for key, val in info_dict['http_headers'].items():
- cmd += ['--header', '%s: %s' % (key, val)]
+ if info_dict.get('http_headers') is not None:
+ for key, val in info_dict['http_headers'].items():
+ cmd += ['--header', '%s: %s' % (key, val)]
cmd += self._option('--interface', 'source_address')
cmd += self._option('--all-proxy', 'proxy')
cmd += self._bool_option('--check-certificate', 'nocheckcertificate', 'false', 'true', '=')
@@ -206,8 +211,10 @@ class HttpieFD(ExternalFD):
def _make_cmd(self, tmpfilename, info_dict):
cmd = ['http', '--download', '--output', tmpfilename, info_dict['url']]
- for key, val in info_dict['http_headers'].items():
- cmd += ['%s:%s' % (key, val)]
+
+ if info_dict.get('http_headers') is not None:
+ for key, val in info_dict['http_headers'].items():
+ cmd += ['%s:%s' % (key, val)]
return cmd
@@ -253,7 +260,7 @@ class FFmpegFD(ExternalFD):
# if end_time:
# args += ['-t', compat_str(end_time - start_time)]
- if info_dict['http_headers'] and re.match(r'^https?://', url):
+ if info_dict.get('http_headers') is not None and re.match(r'^https?://', url):
# Trailing \r\n after each HTTP header is important to prevent warning from ffmpeg/avconv:
# [http @ 00000000003d2fa0] No trailing CRLF found in HTTP header.
headers = handle_youtubedl_headers(info_dict['http_headers'])
diff --git a/youtube_dlc/extractor/extractors.py b/youtube_dlc/extractor/extractors.py
index 24c107598..c77ca12cc 100644
--- a/youtube_dlc/extractor/extractors.py
+++ b/youtube_dlc/extractor/extractors.py
@@ -1175,6 +1175,7 @@ from .theweatherchannel import TheWeatherChannelIE
from .thisamericanlife import ThisAmericanLifeIE
from .thisav import ThisAVIE
from .thisoldhouse import ThisOldHouseIE
+from .thisvid import ThisVidIE
from .threeqsdn import ThreeQSDNIE
from .tiktok import TikTokIE
from .tinypic import TinyPicIE
diff --git a/youtube_dlc/extractor/thisvid.py b/youtube_dlc/extractor/thisvid.py
new file mode 100644
index 000000000..f507e1b06
--- /dev/null
+++ b/youtube_dlc/extractor/thisvid.py
@@ -0,0 +1,97 @@
+# coding: utf-8
+from __future__ import unicode_literals
+import re
+
+from .common import InfoExtractor
+
+
+class ThisVidIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?thisvid\.com/(?P<type>videos|embed)/(?P<id>[A-Za-z0-9-]+/?)'
+ _TESTS = [{
+ 'url': 'https://thisvid.com/videos/french-boy-pantsed/',
+ 'md5': '3397979512c682f6b85b3b04989df224',
+ 'info_dict': {
+ 'id': '2400174',
+ 'ext': 'mp4',
+ 'title': 'French Boy Pantsed',
+ 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/2400000/2400174/preview.mp4.jpg',
+ 'age_limit': 18,
+ }
+ }, {
+ 'url': 'https://thisvid.com/embed/2400174/',
+ 'md5': '3397979512c682f6b85b3b04989df224',
+ 'info_dict': {
+ 'id': '2400174',
+ 'ext': 'mp4',
+ 'title': 'French Boy Pantsed',
+ 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/2400000/2400174/preview.mp4.jpg',
+ 'age_limit': 18,
+ }
+ }]
+
+ def _real_extract(self, url):
+ main_id = self._match_id(url)
+ webpage = self._download_webpage(url, main_id)
+
+ # URL decryptor was reversed from version 4.0.4, later verified working with 5.2.0 and may change in the future.
+ kvs_version = self._html_search_regex(r'<script [^>]+?src="https://thisvid\.com/player/kt_player\.js\?v=(\d+(\.\d+)+)">', webpage, 'kvs_version', fatal=False)
+ if not kvs_version.startswith("5."):
+ self.report_warning("Major version change (" + kvs_version + ") in player engine--Download may fail.")
+
+ title = self._html_search_regex(r'<title>(?:Video: )?(.+?)(?: - (?:\w+ porn at )?ThisVid(?:.com| tube))?</title>', webpage, 'title')
+ # video_id, video_url and license_code from the 'flashvars' JSON object:
+ video_id = self._html_search_regex(r"video_id: '([0-9]+)',", webpage, 'video_id')
+ video_url = self._html_search_regex(r"video_url: '(function/0/.+?)',", webpage, 'video_url')
+ license_code = self._html_search_regex(r"license_code: '([0-9$]{16})',", webpage, 'license_code')
+ thumbnail = self._html_search_regex(r"preview_url: '((?:https?:)?//media.thisvid.com/.+?.jpg)',", webpage, 'thumbnail', fatal=False)
+ if thumbnail.startswith("//"):
+ thumbnail = "https:" + thumbnail
+ if (re.match(self._VALID_URL, url).group('type') == "videos"):
+ display_id = main_id
+ else:
+ display_id = self._search_regex(r'<link rel="canonical" href="' + self._VALID_URL + r'">', webpage, 'display_id', fatal=False),
+
+ return {
+ 'id': video_id,
+ 'display_id': display_id,
+ 'title': title,
+ 'url': getrealurl(video_url, license_code),
+ 'thumbnail': thumbnail,
+ 'age_limit': 18,
+ }
+
+
+def getrealurl(video_url, license_code):
+ urlparts = video_url.split('/')[2:]
+ license = getlicensetoken(license_code)
+ newmagic = urlparts[5][:32]
+
+ for o in range(len(newmagic) - 1, -1, -1):
+ new = ""
+ l = (o + sum([int(n) for n in license[o:]])) % 32
+
+ for i in range(0, len(newmagic)):
+ if i == o:
+ new += newmagic[l]
+ elif i == l:
+ new += newmagic[o]
+ else:
+ new += newmagic[i]
+ newmagic = new
+
+ urlparts[5] = newmagic + urlparts[5][32:]
+ return "/".join(urlparts)
+
+
+def getlicensetoken(license):
+ modlicense = license.replace("$", "").replace("0", "1")
+ center = int(len(modlicense) / 2)
+ fronthalf = int(modlicense[:center + 1])
+ backhalf = int(modlicense[center:])
+
+ modlicense = str(4 * abs(fronthalf - backhalf))
+ retval = ""
+ for o in range(0, center + 1):
+ for i in range(1, 5):
+ retval += str((int(license[o + i]) + int(modlicense[o])) % 10)
+ return retval
diff --git a/youtube_dlc/extractor/youtube.py b/youtube_dlc/extractor/youtube.py
index 3ec2581dc..35ac67b49 100644
--- a/youtube_dlc/extractor/youtube.py
+++ b/youtube_dlc/extractor/youtube.py
@@ -300,11 +300,12 @@ class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
# Extract entries from page with "Load more" button
def _entries(self, page, playlist_id):
more_widget_html = content_html = page
+ mobj_reg = r'(?:(?:data-uix-load-more-href="[^"]+?;continuation=)|(?:"continuation":"))(?P<more>[^"]+)"'
for page_num in itertools.count(1):
for entry in self._process_page(content_html):
yield entry
- mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
+ mobj = re.search(mobj_reg, more_widget_html)
if not mobj:
break
@@ -315,7 +316,7 @@ class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
# Downloading page may result in intermittent 5xx HTTP error
# that is usually worked around with a retry
more = self._download_json(
- 'https://www.youtube.com/%s' % mobj.group('more'), playlist_id,
+ 'https://www.youtube.com/browse_ajax?ctoken=%s' % mobj.group('more'), playlist_id,
'Downloading page #%s%s'
% (page_num, ' (retry #%d)' % count if count else ''),
transform_source=uppercase_escape,
@@ -372,7 +373,7 @@ class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
def _process_page(self, content):
for playlist_id in orderedSet(re.findall(
- r'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"',
+ r'"/?playlist\?list=([0-9A-Za-z-_]{10,})"',
content)):
yield self.url_result(
'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist')
diff --git a/youtube_dlc/extractor/zoom.py b/youtube_dlc/extractor/zoom.py
index 003e1f901..038a90297 100644
--- a/youtube_dlc/extractor/zoom.py
+++ b/youtube_dlc/extractor/zoom.py
@@ -13,7 +13,7 @@ from ..utils import (
class ZoomIE(InfoExtractor):
IE_NAME = 'zoom'
- _VALID_URL = r'https://(?:.*).?zoom.us/rec(?:ording)?/play/(?P<id>[A-Za-z0-9\-_]+)'
+ _VALID_URL = r'https://(?:.*).?zoom.us/rec(?:ording)?/(play|share)/(?P<id>[A-Za-z0-9\-_.]+)'
_TEST = {
'url': 'https://zoom.us/recording/play/SILVuCL4bFtRwWTtOCFQQxAsBQsJljFtm9e4Z_bvo-A8B-nzUSYZRNuPl3qW5IGK',
generated by cgit v1.2.3 (git 2.25.1) at 2025-06-18 18:57:05 +0000