mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-12-30 05:57:01 -05:00
[cleanup] Misc (#10807)
Closes #10751, Closes #10769, Closes #10791 Authored by: bashonly, Codenade, pzhlkj6612, seproDev, coletdjnz, grqz, Grub4K Co-authored-by: Codenade <amadeus.dorian04@gmail.com> Co-authored-by: Mozi <29089388+pzhlkj6612@users.noreply.github.com> Co-authored-by: sepro <4618135+seproDev@users.noreply.github.com> Co-authored-by: coletdjnz <coletdjnz@protonmail.com> Co-authored-by: N/Ame <173015200+grqz@users.noreply.github.com> Co-authored-by: Simon Sawicki <contact@grub4k.xyz>
This commit is contained in:
parent
cca534cd9e
commit
c6387abc1a
2
.github/workflows/quick-test.yml
vendored
2
.github/workflows/quick-test.yml
vendored
@ -15,7 +15,7 @@ jobs:
|
||||
with:
|
||||
python-version: '3.8'
|
||||
- name: Install test requirements
|
||||
run: python3 ./devscripts/install_deps.py --include test
|
||||
run: python3 ./devscripts/install_deps.py -o --include test
|
||||
- name: Run tests
|
||||
timeout-minutes: 15
|
||||
run: |
|
||||
|
4
.github/workflows/release.yml
vendored
4
.github/workflows/release.yml
vendored
@ -204,7 +204,7 @@ jobs:
|
||||
git config --global user.email "41898282+github-actions[bot]@users.noreply.github.com"
|
||||
git add -u
|
||||
git commit -m "Release ${{ env.version }}" \
|
||||
-m "Created by: ${{ github.event.sender.login }}" -m ":ci skip all :ci run dl"
|
||||
-m "Created by: ${{ github.event.sender.login }}" -m ":ci skip all"
|
||||
git push origin --force ${{ github.event.ref }}:release
|
||||
|
||||
- name: Get target commitish
|
||||
@ -325,7 +325,7 @@ jobs:
|
||||
"(https://github.com/yt-dlp/yt-dlp-master-builds/releases/latest \"Master builds\")"' || '' }} > ./RELEASE_NOTES
|
||||
printf '\n\n' >> ./RELEASE_NOTES
|
||||
cat >> ./RELEASE_NOTES << EOF
|
||||
#### A description of the various files are in the [README](https://github.com/${{ github.repository }}#release-files)
|
||||
#### A description of the various files is in the [README](https://github.com/${{ github.repository }}#release-files)
|
||||
---
|
||||
$(python ./devscripts/make_changelog.py -vv --collapsible)
|
||||
EOF
|
||||
|
30
README.md
30
README.md
@ -200,7 +200,7 @@ While all the other dependencies are optional, `ffmpeg` and `ffprobe` are highly
|
||||
|
||||
The following provide support for impersonating browser requests. This may be required for some sites that employ TLS fingerprinting.
|
||||
|
||||
* [**curl_cffi**](https://github.com/yifeikong/curl_cffi) (recommended) - Python binding for [curl-impersonate](https://github.com/lwthiker/curl-impersonate). Provides impersonation targets for Chrome, Edge and Safari. Licensed under [MIT](https://github.com/yifeikong/curl_cffi/blob/main/LICENSE)
|
||||
* [**curl_cffi**](https://github.com/lexiforest/curl_cffi) (recommended) - Python binding for [curl-impersonate](https://github.com/lexiforest/curl-impersonate). Provides impersonation targets for Chrome, Edge and Safari. Licensed under [MIT](https://github.com/lexiforest/curl_cffi/blob/main/LICENSE)
|
||||
* Can be installed with the `curl-cffi` group, e.g. `pip install "yt-dlp[default,curl-cffi]"`
|
||||
* Currently included in `yt-dlp.exe`, `yt-dlp_linux` and `yt-dlp_macos` builds
|
||||
|
||||
@ -459,17 +459,17 @@ If you fork the project on GitHub, you can run your fork's [build workflow](.git
|
||||
conditions. Use a "\" to escape "&" or
|
||||
quotes if needed. If used multiple times,
|
||||
the filter matches if at least one of the
|
||||
conditions is met. E.g. --match-filter
|
||||
!is_live --match-filter "like_count>?100 &
|
||||
conditions is met. E.g. --match-filters
|
||||
!is_live --match-filters "like_count>?100 &
|
||||
description~='(?i)\bcats \& dogs\b'" matches
|
||||
only videos that are not live OR those that
|
||||
have a like count more than 100 (or the like
|
||||
field is not available) and also has a
|
||||
description that contains the phrase "cats &
|
||||
dogs" (caseless). Use "--match-filter -" to
|
||||
dogs" (caseless). Use "--match-filters -" to
|
||||
interactively ask whether to download each
|
||||
video
|
||||
--no-match-filters Do not use any --match-filter (default)
|
||||
--no-match-filters Do not use any --match-filters (default)
|
||||
--break-match-filters FILTER Same as "--match-filters" but stops the
|
||||
download process when a video is rejected
|
||||
--no-break-match-filters Do not use any --break-match-filters (default)
|
||||
@ -490,7 +490,7 @@ If you fork the project on GitHub, you can run your fork's [build workflow](.git
|
||||
encountering a file that is in the archive
|
||||
(default)
|
||||
--break-per-input Alters --max-downloads, --break-on-existing,
|
||||
--break-match-filter, and autonumber to
|
||||
--break-match-filters, and autonumber to
|
||||
reset per input URL
|
||||
--no-break-per-input --break-on-existing and similar options
|
||||
terminates the entire download queue
|
||||
@ -1771,7 +1771,7 @@ The following extractors use this feature:
|
||||
#### youtube
|
||||
* `lang`: Prefer translated metadata (`title`, `description` etc) of this language code (case-sensitive). By default, the video primary language metadata is preferred, with a fallback to `en` translated. See [youtube.py](https://github.com/yt-dlp/yt-dlp/blob/c26f9b991a0681fd3ea548d535919cec1fbbd430/yt_dlp/extractor/youtube.py#L381-L390) for list of supported content language codes
|
||||
* `skip`: One or more of `hls`, `dash` or `translated_subs` to skip extraction of the m3u8 manifests, dash manifests and [auto-translated subtitles](https://github.com/yt-dlp/yt-dlp/issues/4090#issuecomment-1158102032) respectively
|
||||
* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music` and `_creator` (e.g. `ios_creator`); and `mediaconnect`, `mweb`, `android_producer`, `android_testsuite`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `ios,web_creator` is used, and `tv_embedded`, `web_creator` and `mediaconnect` are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. Most `android` clients will be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients.
|
||||
* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music` and `_creator` (e.g. `ios_creator`); and `mediaconnect`, `mweb`, `android_producer`, `android_testsuite`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `ios,web_creator` is used, and `tv_embedded`, `web_creator` and `mediaconnect` are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. Most `android` clients will be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients. You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=all,-web`
|
||||
* `player_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause some issues. See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) for more details
|
||||
* `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp.
|
||||
* `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side)
|
||||
@ -2184,9 +2184,9 @@ with yt_dlp.YoutubeDL(ydl_opts) as ydl:
|
||||
|
||||
* **Output template improvements**: Output templates can now have date-time formatting, numeric offsets, object traversal etc. See [output template](#output-template) for details. Even more advanced operations can also be done with the help of `--parse-metadata` and `--replace-in-metadata`
|
||||
|
||||
* **Other new options**: Many new options have been added such as `--alias`, `--print`, `--concat-playlist`, `--wait-for-video`, `--retry-sleep`, `--sleep-requests`, `--convert-thumbnails`, `--force-download-archive`, `--force-overwrites`, `--break-match-filter` etc
|
||||
* **Other new options**: Many new options have been added such as `--alias`, `--print`, `--concat-playlist`, `--wait-for-video`, `--retry-sleep`, `--sleep-requests`, `--convert-thumbnails`, `--force-download-archive`, `--force-overwrites`, `--break-match-filters` etc
|
||||
|
||||
* **Improvements**: Regex and other operators in `--format`/`--match-filter`, multiple `--postprocessor-args` and `--downloader-args`, faster archive checking, more [format selection options](#format-selection), merge multi-video/audio, multiple `--config-locations`, `--exec` at different stages, etc
|
||||
* **Improvements**: Regex and other operators in `--format`/`--match-filters`, multiple `--postprocessor-args` and `--downloader-args`, faster archive checking, more [format selection options](#format-selection), merge multi-video/audio, multiple `--config-locations`, `--exec` at different stages, etc
|
||||
|
||||
* **Plugins**: Extractors and PostProcessors can be loaded from an external file. See [plugins](#plugins) for details
|
||||
|
||||
@ -2227,7 +2227,7 @@ Some of yt-dlp's default options are different from that of youtube-dl and youtu
|
||||
* `certifi` will be used for SSL root certificates, if installed. If you want to use system certificates (e.g. self-signed), use `--compat-options no-certifi`
|
||||
* yt-dlp's sanitization of invalid characters in filenames is different/smarter than in youtube-dl. You can use `--compat-options filename-sanitization` to revert to youtube-dl's behavior
|
||||
* ~~yt-dlp tries to parse the external downloader outputs into the standard progress output if possible (Currently implemented: [aria2c](https://github.com/yt-dlp/yt-dlp/issues/5931)). You can use `--compat-options no-external-downloader-progress` to get the downloader output as-is~~
|
||||
* yt-dlp versions between 2021.09.01 and 2023.01.02 applies `--match-filter` to nested playlists. This was an unintentional side-effect of [8f18ac](https://github.com/yt-dlp/yt-dlp/commit/8f18aca8717bb0dd49054555af8d386e5eda3a88) and is fixed in [d7b460](https://github.com/yt-dlp/yt-dlp/commit/d7b460d0e5fc710950582baed2e3fc616ed98a80). Use `--compat-options playlist-match-filter` to revert this
|
||||
* yt-dlp versions between 2021.09.01 and 2023.01.02 applies `--match-filters` to nested playlists. This was an unintentional side-effect of [8f18ac](https://github.com/yt-dlp/yt-dlp/commit/8f18aca8717bb0dd49054555af8d386e5eda3a88) and is fixed in [d7b460](https://github.com/yt-dlp/yt-dlp/commit/d7b460d0e5fc710950582baed2e3fc616ed98a80). Use `--compat-options playlist-match-filter` to revert this
|
||||
* yt-dlp versions between 2021.11.10 and 2023.06.21 estimated `filesize_approx` values for fragmented/manifest formats. This was added for convenience in [f2fe69](https://github.com/yt-dlp/yt-dlp/commit/f2fe69c7b0d208bdb1f6292b4ae92bc1e1a7444a), but was reverted in [0dff8e](https://github.com/yt-dlp/yt-dlp/commit/0dff8e4d1e6e9fb938f4256ea9af7d81f42fd54f) due to the potentially extreme inaccuracy of the estimated values. Use `--compat-options manifest-filesize-approx` to keep extracting the estimated values
|
||||
* yt-dlp uses modern http client backends such as `requests`. Use `--compat-options prefer-legacy-http-handler` to prefer the legacy http handler (`urllib`) to be used for standard http requests.
|
||||
* The sub-modules `swfinterp`, `casefold` are removed.
|
||||
@ -2273,11 +2273,11 @@ While these options are redundant, they are still expected to be used due to the
|
||||
--get-thumbnail --print thumbnail
|
||||
-e, --get-title --print title
|
||||
-g, --get-url --print urls
|
||||
--match-title REGEX --match-filter "title ~= (?i)REGEX"
|
||||
--reject-title REGEX --match-filter "title !~= (?i)REGEX"
|
||||
--min-views COUNT --match-filter "view_count >=? COUNT"
|
||||
--max-views COUNT --match-filter "view_count <=? COUNT"
|
||||
--break-on-reject Use --break-match-filter
|
||||
--match-title REGEX --match-filters "title ~= (?i)REGEX"
|
||||
--reject-title REGEX --match-filters "title !~= (?i)REGEX"
|
||||
--min-views COUNT --match-filters "view_count >=? COUNT"
|
||||
--max-views COUNT --match-filters "view_count <=? COUNT"
|
||||
--break-on-reject Use --break-match-filters
|
||||
--user-agent UA --add-header "User-Agent:UA"
|
||||
--referer URL --add-header "Referer:URL"
|
||||
--playlist-start NUMBER -I NUMBER:
|
||||
|
@ -76,7 +76,7 @@ dev = [
|
||||
]
|
||||
static-analysis = [
|
||||
"autopep8~=2.0",
|
||||
"ruff~=0.5.0",
|
||||
"ruff~=0.6.0",
|
||||
]
|
||||
test = [
|
||||
"pytest~=8.1",
|
||||
|
@ -508,7 +508,7 @@ class FFmpegFD(ExternalFD):
|
||||
env = None
|
||||
proxy = self.params.get('proxy')
|
||||
if proxy:
|
||||
if not re.match(r'^[\da-zA-Z]+://', proxy):
|
||||
if not re.match(r'[\da-zA-Z]+://', proxy):
|
||||
proxy = f'http://{proxy}'
|
||||
|
||||
if proxy.startswith('socks'):
|
||||
@ -559,7 +559,7 @@ class FFmpegFD(ExternalFD):
|
||||
|
||||
selected_formats = info_dict.get('requested_formats') or [info_dict]
|
||||
for i, fmt in enumerate(selected_formats):
|
||||
is_http = re.match(r'^https?://', fmt['url'])
|
||||
is_http = re.match(r'https?://', fmt['url'])
|
||||
cookies = self.ydl.cookiejar.get_cookies_for_url(fmt['url']) if is_http else []
|
||||
if cookies:
|
||||
args.extend(['-cookies', ''.join(
|
||||
|
@ -4,7 +4,7 @@ from .common import InfoExtractor
|
||||
|
||||
|
||||
class AcademicEarthCourseIE(InfoExtractor):
|
||||
_VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)'
|
||||
IE_NAME = 'AcademicEarth:Course'
|
||||
_TEST = {
|
||||
'url': 'http://academicearth.org/playlists/laws-of-nature/',
|
||||
|
@ -231,7 +231,7 @@ class ARDIE(InfoExtractor):
|
||||
|
||||
class ARDBetaMediathekIE(InfoExtractor):
|
||||
IE_NAME = 'ARDMediathek'
|
||||
_VALID_URL = r'''(?x)https://
|
||||
_VALID_URL = r'''(?x)https?://
|
||||
(?:(?:beta|www)\.)?ardmediathek\.de/
|
||||
(?:[^/]+/)?
|
||||
(?:player|live|video)/
|
||||
@ -470,7 +470,7 @@ class ARDBetaMediathekIE(InfoExtractor):
|
||||
|
||||
|
||||
class ARDMediathekCollectionIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)https://
|
||||
_VALID_URL = r'''(?x)https?://
|
||||
(?:(?:beta|www)\.)?ardmediathek\.de/
|
||||
(?:[^/?#]+/)?
|
||||
(?P<playlist>sendung|serie|sammlung)/
|
||||
|
@ -3,7 +3,7 @@ from ..utils import float_or_none, int_or_none, make_archive_id, traverse_obj
|
||||
|
||||
|
||||
class CallinIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?callin\.com/(episode)/(?P<id>[-a-zA-Z]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?callin\.com/episode/(?P<id>[-a-zA-Z]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.callin.com/episode/the-title-ix-regime-and-the-long-march-through-EBfXYSrsjc',
|
||||
'info_dict': {
|
||||
|
@ -2077,7 +2077,7 @@ class InfoExtractor:
|
||||
has_drm = HlsFD._has_drm(m3u8_doc)
|
||||
|
||||
def format_url(url):
|
||||
return url if re.match(r'^https?://', url) else urllib.parse.urljoin(m3u8_url, url)
|
||||
return url if re.match(r'https?://', url) else urllib.parse.urljoin(m3u8_url, url)
|
||||
|
||||
if self.get_param('hls_split_discontinuity', False):
|
||||
def _extract_m3u8_playlist_indices(manifest_url=None, m3u8_doc=None):
|
||||
@ -2812,11 +2812,11 @@ class InfoExtractor:
|
||||
base_url_e = element.find(_add_ns('BaseURL'))
|
||||
if try_call(lambda: base_url_e.text) is not None:
|
||||
base_url = base_url_e.text + base_url
|
||||
if re.match(r'^https?://', base_url):
|
||||
if re.match(r'https?://', base_url):
|
||||
break
|
||||
if mpd_base_url and base_url.startswith('/'):
|
||||
base_url = urllib.parse.urljoin(mpd_base_url, base_url)
|
||||
elif mpd_base_url and not re.match(r'^https?://', base_url):
|
||||
elif mpd_base_url and not re.match(r'https?://', base_url):
|
||||
if not mpd_base_url.endswith('/'):
|
||||
mpd_base_url += '/'
|
||||
base_url = mpd_base_url + base_url
|
||||
@ -2906,7 +2906,7 @@ class InfoExtractor:
|
||||
}
|
||||
|
||||
def location_key(location):
|
||||
return 'url' if re.match(r'^https?://', location) else 'path'
|
||||
return 'url' if re.match(r'https?://', location) else 'path'
|
||||
|
||||
if 'segment_urls' not in representation_ms_info and 'media' in representation_ms_info:
|
||||
|
||||
|
@ -14,7 +14,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class FC2IE(InfoExtractor):
|
||||
_VALID_URL = r'^(?:https?://video\.fc2\.com/(?:[^/]+/)*content/|fc2:)(?P<id>[^/]+)'
|
||||
_VALID_URL = r'(?:https?://video\.fc2\.com/(?:[^/]+/)*content/|fc2:)(?P<id>[^/]+)'
|
||||
IE_NAME = 'fc2'
|
||||
_NETRC_MACHINE = 'fc2'
|
||||
_TESTS = [{
|
||||
|
@ -2340,7 +2340,7 @@ class GenericIE(InfoExtractor):
|
||||
default_search = 'fixup_error'
|
||||
|
||||
if default_search in ('auto', 'auto_warning', 'fixup_error'):
|
||||
if re.match(r'^[^\s/]+\.[^\s/]+/', url):
|
||||
if re.match(r'[^\s/]+\.[^\s/]+/', url):
|
||||
self.report_warning('The url doesn\'t specify the protocol, trying with http')
|
||||
return self.url_result('http://' + url)
|
||||
elif default_search != 'fixup_error':
|
||||
@ -2400,7 +2400,7 @@ class GenericIE(InfoExtractor):
|
||||
|
||||
# Check for direct link to a video
|
||||
content_type = full_response.headers.get('Content-Type', '').lower()
|
||||
m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
|
||||
m = re.match(r'(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
|
||||
if m:
|
||||
self.report_detected('direct video link')
|
||||
headers = filter_dict({'Referer': smuggled_data.get('referer')})
|
||||
|
@ -52,7 +52,7 @@ class GetCourseRuIE(InfoExtractor):
|
||||
_BASE_URL_RE = rf'https?://(?:(?!player02\.)[^.]+\.getcourse\.(?:ru|io)|{"|".join(map(re.escape, _DOMAINS))})'
|
||||
_VALID_URL = [
|
||||
rf'{_BASE_URL_RE}/(?!pl/|teach/)(?P<id>[^?#]+)',
|
||||
rf'{_BASE_URL_RE}/(:?pl/)?teach/control/lesson/view\?(?:[^#]+&)?id=(?P<id>\d+)',
|
||||
rf'{_BASE_URL_RE}/(?:pl/)?teach/control/lesson/view\?(?:[^#]+&)?id=(?P<id>\d+)',
|
||||
]
|
||||
_TESTS = [{
|
||||
'url': 'http://academymel.online/3video_1',
|
||||
|
@ -7,7 +7,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class GolemIE(InfoExtractor):
|
||||
_VALID_URL = r'^https?://video\.golem\.de/.+?/(?P<id>.+?)/'
|
||||
_VALID_URL = r'https?://video\.golem\.de/.+?/(?P<id>.+?)/'
|
||||
_TEST = {
|
||||
'url': 'http://video.golem.de/handy/14095/iphone-6-und-6-plus-test.html',
|
||||
'md5': 'c1a2c0a3c863319651c7c992c5ee29bf',
|
||||
|
@ -13,7 +13,7 @@ from ..utils import (
|
||||
|
||||
class HRFernsehenIE(InfoExtractor):
|
||||
IE_NAME = 'hrfernsehen'
|
||||
_VALID_URL = r'^https?://www\.(?:hr-fernsehen|hessenschau)\.de/.*,video-(?P<id>[0-9]{6})\.html'
|
||||
_VALID_URL = r'https?://www\.(?:hr-fernsehen|hessenschau)\.de/.*,video-(?P<id>[0-9]{6})\.html'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.hessenschau.de/tv-sendung/hessenschau-vom-26082020,video-130546.html',
|
||||
'md5': '5c4e0ba94677c516a2f65a84110fc536',
|
||||
|
@ -194,11 +194,14 @@ class ShugiinItvVodIE(ShugiinItvBaseIE):
|
||||
|
||||
|
||||
class SangiinInstructionIE(InfoExtractor):
|
||||
_VALID_URL = r'^https?://www\.webtv\.sangiin\.go\.jp/webtv/index\.php'
|
||||
_VALID_URL = r'https?://www\.webtv\.sangiin\.go\.jp/webtv/index\.php'
|
||||
IE_DESC = False # this shouldn't be listed as a supported site
|
||||
|
||||
def _real_extract(self, url):
|
||||
raise ExtractorError('Copy the link from the botton below the video description or player, and use the link to download. If there are no button in the frame, get the URL of the frame showing the video.', expected=True)
|
||||
raise ExtractorError(
|
||||
'Copy the link from the button below the video description/player '
|
||||
'and use that link to download. If there is no button in the frame, '
|
||||
'get the URL of the frame showing the video.', expected=True)
|
||||
|
||||
|
||||
class SangiinIE(InfoExtractor):
|
||||
|
@ -22,7 +22,7 @@ class KalturaIE(InfoExtractor):
|
||||
(?:
|
||||
kaltura:(?P<partner_id>\w+):(?P<id>\w+)(?::(?P<player_type>\w+))?|
|
||||
https?://
|
||||
(:?(?:www|cdnapi(?:sec)?)\.)?kaltura\.com(?::\d+)?/
|
||||
(?:(?:www|cdnapi(?:sec)?)\.)?kaltura\.com(?::\d+)?/
|
||||
(?:
|
||||
(?:
|
||||
# flash player
|
||||
|
@ -126,7 +126,7 @@ class MailRuIE(InfoExtractor):
|
||||
video_data = None
|
||||
|
||||
# fix meta_url if missing the host address
|
||||
if re.match(r'^\/\+\/', meta_url):
|
||||
if re.match(r'\/\+\/', meta_url):
|
||||
meta_url = urljoin('https://my.mail.ru', meta_url)
|
||||
|
||||
if meta_url:
|
||||
|
@ -16,7 +16,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class MGTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:w(?:ww)?\.)?mgtv\.com/(v|b)/(?:[^/]+/)*(?P<id>\d+)\.html'
|
||||
_VALID_URL = r'https?://(?:w(?:ww)?\.)?mgtv\.com/[bv]/(?:[^/]+/)*(?P<id>\d+)\.html'
|
||||
IE_DESC = '芒果TV'
|
||||
IE_NAME = 'MangoTV'
|
||||
|
||||
|
@ -65,7 +65,7 @@ class TechTVMITIE(InfoExtractor):
|
||||
|
||||
class OCWMITIE(InfoExtractor):
|
||||
IE_NAME = 'ocw.mit.edu'
|
||||
_VALID_URL = r'^https?://ocw\.mit\.edu/courses/(?P<topic>[a-z0-9\-]+)'
|
||||
_VALID_URL = r'https?://ocw\.mit\.edu/courses/(?P<topic>[a-z0-9\-]+)'
|
||||
_BASE_URL = 'http://ocw.mit.edu/'
|
||||
|
||||
_TESTS = [
|
||||
|
@ -10,7 +10,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class NZOnScreenIE(InfoExtractor):
|
||||
_VALID_URL = r'^https?://www\.nzonscreen\.com/title/(?P<id>[^/?#]+)'
|
||||
_VALID_URL = r'https?://www\.nzonscreen\.com/title/(?P<id>[^/?#]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.nzonscreen.com/title/shoop-shoop-diddy-wop-cumma-cumma-wang-dang-1982',
|
||||
'info_dict': {
|
||||
|
@ -628,8 +628,7 @@ class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
|
||||
page_entries = self._extract_entries(webpage, host)
|
||||
if not page_entries:
|
||||
break
|
||||
for e in page_entries:
|
||||
yield e
|
||||
yield from page_entries
|
||||
if not self._has_more(webpage):
|
||||
break
|
||||
|
||||
|
@ -16,7 +16,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class RadioFranceIE(InfoExtractor):
|
||||
_VALID_URL = r'^https?://maison\.radiofrance\.fr/radiovisions/(?P<id>[^?#]+)'
|
||||
_VALID_URL = r'https?://maison\.radiofrance\.fr/radiovisions/(?P<id>[^?#]+)'
|
||||
IE_NAME = 'radiofrance'
|
||||
|
||||
_TEST = {
|
||||
|
@ -6,7 +6,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class ReverbNationIE(InfoExtractor):
|
||||
_VALID_URL = r'^https?://(?:www\.)?reverbnation\.com/.*?/song/(?P<id>\d+).*?$'
|
||||
_VALID_URL = r'https?://(?:www\.)?reverbnation\.com/.*?/song/(?P<id>\d+).*?$'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.reverbnation.com/alkilados/song/16965047-mona-lisa',
|
||||
'md5': 'c0aaf339bcee189495fdf5a8c8ba8645',
|
||||
|
@ -8,7 +8,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class Tele13IE(InfoExtractor):
|
||||
_VALID_URL = r'^https?://(?:www\.)?t13\.cl/videos(?:/[^/]+)+/(?P<id>[\w-]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?t13\.cl/videos(?:/[^/]+)+/(?P<id>[\w-]+)'
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://www.t13.cl/videos/actualidad/el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda',
|
||||
|
@ -270,7 +270,7 @@ class TwitCastingLiveIE(InfoExtractor):
|
||||
|
||||
|
||||
class TwitCastingUserIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:[^/?#]+\.)?twitcasting\.tv/(?P<id>[^/?#]+)/(:?show|archive)/?(?:[#?]|$)'
|
||||
_VALID_URL = r'https?://(?:[^/?#]+\.)?twitcasting\.tv/(?P<id>[^/?#]+)/(?:show|archive)/?(?:[#?]|$)'
|
||||
_TESTS = [{
|
||||
'url': 'https://twitcasting.tv/natsuiromatsuri/archive/',
|
||||
'info_dict': {
|
||||
|
@ -90,7 +90,7 @@ class ViuIE(ViuBaseIE):
|
||||
formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, 'mp4')
|
||||
|
||||
for key, value in video_data.items():
|
||||
mobj = re.match(r'^subtitle_(?P<lang>[^_]+)_(?P<ext>(vtt|srt))', key)
|
||||
mobj = re.match(r'subtitle_(?P<lang>[^_]+)_(?P<ext>(vtt|srt))', key)
|
||||
if not mobj:
|
||||
continue
|
||||
subtitles.setdefault(mobj.group('lang'), []).append({
|
||||
|
@ -21,7 +21,7 @@ class XimalayaBaseIE(InfoExtractor):
|
||||
class XimalayaIE(XimalayaBaseIE):
|
||||
IE_NAME = 'ximalaya'
|
||||
IE_DESC = '喜马拉雅FM'
|
||||
_VALID_URL = r'https?://(?:www\.|m\.)?ximalaya\.com/(:?(?P<uid>\d+)/)?sound/(?P<id>[0-9]+)'
|
||||
_VALID_URL = r'https?://(?:www\.|m\.)?ximalaya\.com/(?:(?P<uid>\d+)/)?sound/(?P<id>[0-9]+)'
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://www.ximalaya.com/sound/47740352/',
|
||||
|
@ -33,8 +33,8 @@ if not websockets:
|
||||
import websockets.version
|
||||
|
||||
websockets_version = tuple(map(int_or_none, websockets.version.version.split('.')))
|
||||
if websockets_version < (12, 0):
|
||||
raise ImportError('Only websockets>=12.0 is supported')
|
||||
if websockets_version < (13, 0):
|
||||
raise ImportError('Only websockets>=13.0 is supported')
|
||||
|
||||
import websockets.sync.client
|
||||
from websockets.uri import parse_uri
|
||||
|
@ -647,16 +647,16 @@ def create_parser():
|
||||
'You can also simply specify a field to match if the field is present, '
|
||||
'use "!field" to check if the field is not present, and "&" to check multiple conditions. '
|
||||
'Use a "\\" to escape "&" or quotes if needed. If used multiple times, '
|
||||
'the filter matches if at least one of the conditions is met. E.g. --match-filter '
|
||||
'!is_live --match-filter "like_count>?100 & description~=\'(?i)\\bcats \\& dogs\\b\'" '
|
||||
'the filter matches if at least one of the conditions is met. E.g. --match-filters '
|
||||
'!is_live --match-filters "like_count>?100 & description~=\'(?i)\\bcats \\& dogs\\b\'" '
|
||||
'matches only videos that are not live OR those that have a like count more than 100 '
|
||||
'(or the like field is not available) and also has a description '
|
||||
'that contains the phrase "cats & dogs" (caseless). '
|
||||
'Use "--match-filter -" to interactively ask whether to download each video'))
|
||||
'Use "--match-filters -" to interactively ask whether to download each video'))
|
||||
selection.add_option(
|
||||
'--no-match-filters',
|
||||
dest='match_filter', action='store_const', const=None,
|
||||
help='Do not use any --match-filter (default)')
|
||||
help='Do not use any --match-filters (default)')
|
||||
selection.add_option(
|
||||
'--break-match-filters',
|
||||
metavar='FILTER', dest='breaking_match_filter', action='append',
|
||||
@ -704,7 +704,7 @@ def create_parser():
|
||||
selection.add_option(
|
||||
'--break-per-input',
|
||||
action='store_true', dest='break_per_url', default=False,
|
||||
help='Alters --max-downloads, --break-on-existing, --break-match-filter, and autonumber to reset per input URL')
|
||||
help='Alters --max-downloads, --break-on-existing, --break-match-filters, and autonumber to reset per input URL')
|
||||
selection.add_option(
|
||||
'--no-break-per-input',
|
||||
action='store_false', dest='break_per_url',
|
||||
|
@ -33,7 +33,7 @@ class SponsorBlockPP(FFmpegPostProcessor):
|
||||
def __init__(self, downloader, categories=None, api='https://sponsor.ajay.app'):
|
||||
FFmpegPostProcessor.__init__(self, downloader)
|
||||
self._categories = tuple(categories or self.CATEGORIES.keys())
|
||||
self._API_URL = api if re.match('^https?://', api) else 'https://' + api
|
||||
self._API_URL = api if re.match('https?://', api) else 'https://' + api
|
||||
|
||||
def run(self, info):
|
||||
extractor = info['extractor_key']
|
||||
|
@ -1954,7 +1954,7 @@ def urljoin(base, path):
|
||||
path = path.decode()
|
||||
if not isinstance(path, str) or not path:
|
||||
return None
|
||||
if re.match(r'^(?:[a-zA-Z][a-zA-Z0-9+-.]*:)?//', path):
|
||||
if re.match(r'(?:[a-zA-Z][a-zA-Z0-9+-.]*:)?//', path):
|
||||
return path
|
||||
if isinstance(base, bytes):
|
||||
base = base.decode()
|
||||
@ -2007,7 +2007,7 @@ def url_or_none(url):
|
||||
if not url or not isinstance(url, str):
|
||||
return None
|
||||
url = url.strip()
|
||||
return url if re.match(r'^(?:(?:https?|rt(?:m(?:pt?[es]?|fp)|sp[su]?)|mms|ftps?):)?//', url) else None
|
||||
return url if re.match(r'(?:(?:https?|rt(?:m(?:pt?[es]?|fp)|sp[su]?)|mms|ftps?):)?//', url) else None
|
||||
|
||||
|
||||
def strftime_or_none(timestamp, date_format='%Y%m%d', default=None):
|
||||
@ -3113,7 +3113,7 @@ def is_html(first_bytes):
|
||||
while first_bytes.startswith(bom):
|
||||
encoding, first_bytes = enc, first_bytes[len(bom):]
|
||||
|
||||
return re.match(r'^\s*<', first_bytes.decode(encoding, 'replace'))
|
||||
return re.match(r'\s*<', first_bytes.decode(encoding, 'replace'))
|
||||
|
||||
|
||||
def determine_protocol(info_dict):
|
||||
|
Loading…
Reference in New Issue
Block a user