aboutsummaryrefslogtreecommitdiffstats
path: root/yt_dlp/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'yt_dlp/extractor')
-rw-r--r--yt_dlp/extractor/abematv.py8
-rw-r--r--yt_dlp/extractor/adobepass.py3
-rw-r--r--yt_dlp/extractor/afreecatv.py5
-rw-r--r--yt_dlp/extractor/bbc.py4
-rw-r--r--yt_dlp/extractor/brightcove.py4
-rw-r--r--yt_dlp/extractor/common.py11
-rw-r--r--yt_dlp/extractor/crunchyroll.py10
-rw-r--r--yt_dlp/extractor/generic.py6
-rw-r--r--yt_dlp/extractor/microsoftvirtualacademy.py9
-rw-r--r--yt_dlp/extractor/mildom.py4
-rw-r--r--yt_dlp/extractor/mixcloud.py3
-rw-r--r--yt_dlp/extractor/mtv.py5
-rw-r--r--yt_dlp/extractor/noz.py3
-rw-r--r--yt_dlp/extractor/openload.py3
-rw-r--r--yt_dlp/extractor/soundcloud.py3
-rw-r--r--yt_dlp/extractor/udemy.py3
-rw-r--r--yt_dlp/extractor/vimeo.py3
17 files changed, 37 insertions, 50 deletions
diff --git a/yt_dlp/extractor/abematv.py b/yt_dlp/extractor/abematv.py
index a839f0c1f..c7db05475 100644
--- a/yt_dlp/extractor/abematv.py
+++ b/yt_dlp/extractor/abematv.py
@@ -5,13 +5,14 @@ import hashlib
import hmac
import re
import struct
+import urllib.response
+import uuid
from base64 import urlsafe_b64encode
from binascii import unhexlify
from .common import InfoExtractor
from ..aes import aes_ecb_decrypt
from ..compat import (
- compat_urllib_response,
compat_urllib_parse_urlparse,
compat_urllib_request,
)
@@ -19,7 +20,6 @@ from ..utils import (
ExtractorError,
decode_base,
int_or_none,
- random_uuidv4,
request_to_url,
time_seconds,
update_url_query,
@@ -141,7 +141,7 @@ class AbemaLicenseHandler(compat_urllib_request.BaseHandler):
url = request_to_url(url)
ticket = compat_urllib_parse_urlparse(url).netloc
response_data = self._get_videokey_from_ticket(ticket)
- return compat_urllib_response.addinfourl(io.BytesIO(response_data), headers={
+ return urllib.response.addinfourl(io.BytesIO(response_data), headers={
'Content-Length': len(response_data),
}, url=url, code=200)
@@ -253,7 +253,7 @@ class AbemaTVIE(AbemaTVBaseIE):
if self._USERTOKEN:
return self._USERTOKEN
- self._DEVICE_ID = random_uuidv4()
+ self._DEVICE_ID = str(uuid.uuid4())
aks = self._generate_aks(self._DEVICE_ID)
user_data = self._download_json(
'https://api.abema.io/v1/users', None, note='Authorizing',
diff --git a/yt_dlp/extractor/adobepass.py b/yt_dlp/extractor/adobepass.py
index 5d98301b8..1292484c6 100644
--- a/yt_dlp/extractor/adobepass.py
+++ b/yt_dlp/extractor/adobepass.py
@@ -8,7 +8,6 @@ import xml.etree.ElementTree as etree
from .common import InfoExtractor
from ..compat import (
- compat_kwargs,
compat_urlparse,
compat_getpass
)
@@ -1365,7 +1364,7 @@ class AdobePassIE(InfoExtractor):
headers.update(kwargs.get('headers', {}))
kwargs['headers'] = headers
return super(AdobePassIE, self)._download_webpage_handle(
- *args, **compat_kwargs(kwargs))
+ *args, **kwargs)
@staticmethod
def _get_mvpd_resource(provider_id, title, guid, rating):
diff --git a/yt_dlp/extractor/afreecatv.py b/yt_dlp/extractor/afreecatv.py
index 28946e9dd..44bfb8bc2 100644
--- a/yt_dlp/extractor/afreecatv.py
+++ b/yt_dlp/extractor/afreecatv.py
@@ -5,7 +5,6 @@ import functools
import re
from .common import InfoExtractor
-from ..compat import compat_xpath
from ..utils import (
ExtractorError,
OnDemandPagedList,
@@ -282,7 +281,7 @@ class AfreecaTVIE(InfoExtractor):
else:
raise ExtractorError('Unable to download video info')
- video_element = video_xml.findall(compat_xpath('./track/video'))[-1]
+ video_element = video_xml.findall('./track/video')[-1]
if video_element is None or video_element.text is None:
raise ExtractorError(
'Video %s does not exist' % video_id, expected=True)
@@ -312,7 +311,7 @@ class AfreecaTVIE(InfoExtractor):
if not video_url:
entries = []
- file_elements = video_element.findall(compat_xpath('./file'))
+ file_elements = video_element.findall('./file')
one = len(file_elements) == 1
for file_num, file_element in enumerate(file_elements, start=1):
file_url = url_or_none(file_element.text)
diff --git a/yt_dlp/extractor/bbc.py b/yt_dlp/extractor/bbc.py
index 29ad7ded7..5bc8d3110 100644
--- a/yt_dlp/extractor/bbc.py
+++ b/yt_dlp/extractor/bbc.py
@@ -1,6 +1,7 @@
# coding: utf-8
from __future__ import unicode_literals
+import xml.etree.ElementTree
import functools
import itertools
import json
@@ -8,7 +9,6 @@ import re
from .common import InfoExtractor
from ..compat import (
- compat_etree_Element,
compat_HTTPError,
compat_str,
compat_urllib_error,
@@ -318,7 +318,7 @@ class BBCCoUkIE(InfoExtractor):
continue
captions = self._download_xml(
cc_url, programme_id, 'Downloading captions', fatal=False)
- if not isinstance(captions, compat_etree_Element):
+ if not isinstance(captions, xml.etree.ElementTree.Element):
continue
subtitles['en'] = [
{
diff --git a/yt_dlp/extractor/brightcove.py b/yt_dlp/extractor/brightcove.py
index dcd332b43..60c853898 100644
--- a/yt_dlp/extractor/brightcove.py
+++ b/yt_dlp/extractor/brightcove.py
@@ -4,6 +4,7 @@ from __future__ import unicode_literals
import base64
import re
import struct
+import xml.etree.ElementTree
from .adobepass import AdobePassIE
from .common import InfoExtractor
@@ -12,7 +13,6 @@ from ..compat import (
compat_HTTPError,
compat_parse_qs,
compat_urlparse,
- compat_xml_parse_error,
)
from ..utils import (
clean_html,
@@ -166,7 +166,7 @@ class BrightcoveLegacyIE(InfoExtractor):
try:
object_doc = compat_etree_fromstring(object_str.encode('utf-8'))
- except compat_xml_parse_error:
+ except xml.etree.ElementTree.ParseError:
return
fv_el = find_xpath_attr(object_doc, './param', 'name', 'flashVars')
diff --git a/yt_dlp/extractor/common.py b/yt_dlp/extractor/common.py
index 48f302f86..8da21a3dc 100644
--- a/yt_dlp/extractor/common.py
+++ b/yt_dlp/extractor/common.py
@@ -3,6 +3,7 @@ from __future__ import unicode_literals
import base64
import collections
+import xml.etree.ElementTree
import hashlib
import itertools
import json
@@ -17,7 +18,6 @@ import math
from ..compat import (
compat_cookiejar_Cookie,
compat_cookies_SimpleCookie,
- compat_etree_Element,
compat_etree_fromstring,
compat_expanduser,
compat_getpass,
@@ -30,7 +30,6 @@ from ..compat import (
compat_urllib_parse_urlencode,
compat_urllib_request,
compat_urlparse,
- compat_xml_parse_error,
)
from ..downloader import FileDownloader
from ..downloader.f4m import (
@@ -951,7 +950,7 @@ class InfoExtractor(object):
fatal=True, encoding=None, data=None, headers={}, query={},
expected_status=None):
"""
- Return a tuple (xml as an compat_etree_Element, URL handle).
+ Return a tuple (xml as an xml.etree.ElementTree.Element, URL handle).
See _download_webpage docstring for arguments specification.
"""
@@ -972,7 +971,7 @@ class InfoExtractor(object):
transform_source=None, fatal=True, encoding=None,
data=None, headers={}, query={}, expected_status=None):
"""
- Return the xml as an compat_etree_Element.
+ Return the xml as an xml.etree.ElementTree.Element.
See _download_webpage docstring for arguments specification.
"""
@@ -988,7 +987,7 @@ class InfoExtractor(object):
xml_string = transform_source(xml_string)
try:
return compat_etree_fromstring(xml_string.encode('utf-8'))
- except compat_xml_parse_error as ve:
+ except xml.etree.ElementTree.ParseError as ve:
errmsg = '%s: Failed to parse XML ' % video_id
if fatal:
raise ExtractorError(errmsg, cause=ve)
@@ -2008,7 +2007,7 @@ class InfoExtractor(object):
def _parse_f4m_formats(self, manifest, manifest_url, video_id, preference=None, quality=None, f4m_id=None,
transform_source=lambda s: fix_xml_ampersands(s).strip(),
fatal=True, m3u8_id=None):
- if not isinstance(manifest, compat_etree_Element) and not fatal:
+ if not isinstance(manifest, xml.etree.ElementTree.Element) and not fatal:
return []
# currently yt-dlp cannot decode the playerVerificationChallenge as Akamai uses Adobe Alchemy
diff --git a/yt_dlp/extractor/crunchyroll.py b/yt_dlp/extractor/crunchyroll.py
index 7edb645f8..d7696bbd9 100644
--- a/yt_dlp/extractor/crunchyroll.py
+++ b/yt_dlp/extractor/crunchyroll.py
@@ -6,13 +6,13 @@ import re
import json
import zlib
+import xml.etree.ElementTree
from hashlib import sha1
from math import pow, sqrt, floor
from .common import InfoExtractor
from .vrv import VRVBaseIE
from ..compat import (
compat_b64decode,
- compat_etree_Element,
compat_etree_fromstring,
compat_str,
compat_urllib_parse_urlencode,
@@ -395,7 +395,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
'Downloading subtitles for ' + sub_name, data={
'subtitle_script_id': sub_id,
})
- if not isinstance(sub_doc, compat_etree_Element):
+ if not isinstance(sub_doc, xml.etree.ElementTree.Element):
continue
sid = sub_doc.get('id')
iv = xpath_text(sub_doc, 'iv', 'subtitle iv')
@@ -525,7 +525,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
'video_quality': stream_quality,
'current_page': url,
})
- if isinstance(streamdata, compat_etree_Element):
+ if isinstance(streamdata, xml.etree.ElementTree.Element):
stream_info = streamdata.find('./{default}preload/stream_info')
if stream_info is not None:
stream_infos.append(stream_info)
@@ -536,7 +536,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
'video_format': stream_format,
'video_encode_quality': stream_quality,
})
- if isinstance(stream_info, compat_etree_Element):
+ if isinstance(stream_info, xml.etree.ElementTree.Element):
stream_infos.append(stream_info)
for stream_info in stream_infos:
video_encode_id = xpath_text(stream_info, './video_encode_id')
@@ -611,7 +611,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
season = episode = episode_number = duration = None
- if isinstance(metadata, compat_etree_Element):
+ if isinstance(metadata, xml.etree.ElementTree.Element):
season = xpath_text(metadata, 'series_title')
episode = xpath_text(metadata, 'episode_title')
episode_number = int_or_none(xpath_text(metadata, 'episode_number'))
diff --git a/yt_dlp/extractor/generic.py b/yt_dlp/extractor/generic.py
index f11fc844d..fd620217e 100644
--- a/yt_dlp/extractor/generic.py
+++ b/yt_dlp/extractor/generic.py
@@ -4,6 +4,7 @@ from __future__ import unicode_literals
import os
import re
+import xml.etree.ElementTree
from .common import InfoExtractor
from .youtube import YoutubeIE
@@ -12,7 +13,6 @@ from ..compat import (
compat_str,
compat_urllib_parse_unquote,
compat_urlparse,
- compat_xml_parse_error,
)
from ..utils import (
determine_ext,
@@ -2827,7 +2827,7 @@ class GenericIE(InfoExtractor):
try:
try:
doc = compat_etree_fromstring(webpage)
- except compat_xml_parse_error:
+ except xml.etree.ElementTree.ParseError:
doc = compat_etree_fromstring(webpage.encode('utf-8'))
if doc.tag == 'rss':
self.report_detected('RSS feed')
@@ -2862,7 +2862,7 @@ class GenericIE(InfoExtractor):
self.report_detected('F4M manifest')
self._sort_formats(info_dict['formats'])
return info_dict
- except compat_xml_parse_error:
+ except xml.etree.ElementTree.ParseError:
pass
# Is it a Camtasia project?
diff --git a/yt_dlp/extractor/microsoftvirtualacademy.py b/yt_dlp/extractor/microsoftvirtualacademy.py
index 46abd2a6d..9255a7964 100644
--- a/yt_dlp/extractor/microsoftvirtualacademy.py
+++ b/yt_dlp/extractor/microsoftvirtualacademy.py
@@ -3,9 +3,6 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..compat import (
- compat_xpath,
-)
from ..utils import (
int_or_none,
parse_duration,
@@ -70,9 +67,9 @@ class MicrosoftVirtualAcademyIE(MicrosoftVirtualAcademyBaseIE):
formats = []
- for sources in settings.findall(compat_xpath('.//MediaSources')):
+ for sources in settings.findall('.//MediaSources'):
sources_type = sources.get('videoType')
- for source in sources.findall(compat_xpath('./MediaSource')):
+ for source in sources.findall('./MediaSource'):
video_url = source.text
if not video_url or not video_url.startswith('http'):
continue
@@ -101,7 +98,7 @@ class MicrosoftVirtualAcademyIE(MicrosoftVirtualAcademyBaseIE):
self._sort_formats(formats)
subtitles = {}
- for source in settings.findall(compat_xpath('.//MarkerResourceSource')):
+ for source in settings.findall('.//MarkerResourceSource'):
subtitle_url = source.text
if not subtitle_url:
continue
diff --git a/yt_dlp/extractor/mildom.py b/yt_dlp/extractor/mildom.py
index 5f2df29c6..4de8e9ef4 100644
--- a/yt_dlp/extractor/mildom.py
+++ b/yt_dlp/extractor/mildom.py
@@ -3,6 +3,7 @@ from __future__ import unicode_literals
import functools
import json
+import uuid
from .common import InfoExtractor
from ..utils import (
@@ -11,7 +12,6 @@ from ..utils import (
ExtractorError,
float_or_none,
OnDemandPagedList,
- random_uuidv4,
traverse_obj,
)
@@ -21,7 +21,7 @@ class MildomBaseIE(InfoExtractor):
def _call_api(self, url, video_id, query=None, note='Downloading JSON metadata', body=None):
if not self._GUEST_ID:
- self._GUEST_ID = f'pc-gp-{random_uuidv4()}'
+ self._GUEST_ID = f'pc-gp-{str(uuid.uuid4())}'
content = self._download_json(
url, video_id, note=note, data=json.dumps(body).encode() if body else None,
diff --git a/yt_dlp/extractor/mixcloud.py b/yt_dlp/extractor/mixcloud.py
index c2dd078ac..b19e59b1a 100644
--- a/yt_dlp/extractor/mixcloud.py
+++ b/yt_dlp/extractor/mixcloud.py
@@ -9,7 +9,6 @@ from ..compat import (
compat_ord,
compat_str,
compat_urllib_parse_unquote,
- compat_zip
)
from ..utils import (
ExtractorError,
@@ -76,7 +75,7 @@ class MixcloudIE(MixcloudBaseIE):
"""Encrypt/Decrypt XOR cipher. Both ways are possible because it's XOR."""
return ''.join([
compat_chr(compat_ord(ch) ^ compat_ord(k))
- for ch, k in compat_zip(ciphertext, itertools.cycle(key))])
+ for ch, k in zip(ciphertext, itertools.cycle(key))])
def _real_extract(self, url):
username, slug = self._match_valid_url(url).groups()
diff --git a/yt_dlp/extractor/mtv.py b/yt_dlp/extractor/mtv.py
index be5de0a70..cff314e27 100644
--- a/yt_dlp/extractor/mtv.py
+++ b/yt_dlp/extractor/mtv.py
@@ -6,7 +6,6 @@ import re
from .common import InfoExtractor
from ..compat import (
compat_str,
- compat_xpath,
)
from ..utils import (
ExtractorError,
@@ -167,9 +166,9 @@ class MTVServicesInfoExtractor(InfoExtractor):
itemdoc, './/{http://search.yahoo.com/mrss/}category',
'scheme', 'urn:mtvn:video_title')
if title_el is None:
- title_el = itemdoc.find(compat_xpath('.//{http://search.yahoo.com/mrss/}title'))
+ title_el = itemdoc.find('.//{http://search.yahoo.com/mrss/}title')
if title_el is None:
- title_el = itemdoc.find(compat_xpath('.//title'))
+ title_el = itemdoc.find('.//title')
if title_el.text is None:
title_el = None
diff --git a/yt_dlp/extractor/noz.py b/yt_dlp/extractor/noz.py
index ccafd7723..bdc2efcd7 100644
--- a/yt_dlp/extractor/noz.py
+++ b/yt_dlp/extractor/noz.py
@@ -4,7 +4,6 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_unquote,
- compat_xpath,
)
from ..utils import (
int_or_none,
@@ -50,7 +49,7 @@ class NozIE(InfoExtractor):
duration = int_or_none(xpath_text(
doc, './/article/movie/file/duration'))
formats = []
- for qnode in doc.findall(compat_xpath('.//article/movie/file/qualities/qual')):
+ for qnode in doc.findall('.//article/movie/file/qualities/qual'):
http_url_ele = find_xpath_attr(
qnode, './html_urls/video_url', 'format', 'video/mp4')
http_url = http_url_ele.text if http_url_ele is not None else None
diff --git a/yt_dlp/extractor/openload.py b/yt_dlp/extractor/openload.py
index fe4740aae..c19d04900 100644
--- a/yt_dlp/extractor/openload.py
+++ b/yt_dlp/extractor/openload.py
@@ -8,7 +8,6 @@ import tempfile
from ..compat import (
compat_urlparse,
- compat_kwargs,
)
from ..utils import (
check_executable,
@@ -158,7 +157,7 @@ class PhantomJSwrapper(object):
cookie['rest'] = {'httpOnly': None}
if 'expiry' in cookie:
cookie['expire_time'] = cookie['expiry']
- self.extractor._set_cookie(**compat_kwargs(cookie))
+ self.extractor._set_cookie(**cookie)
def get(self, url, html=None, video_id=None, note=None, note2='Executing JS on webpage', headers={}, jscode='saveAndExit();'):
"""
diff --git a/yt_dlp/extractor/soundcloud.py b/yt_dlp/extractor/soundcloud.py
index bbc79c2be..749e6dda3 100644
--- a/yt_dlp/extractor/soundcloud.py
+++ b/yt_dlp/extractor/soundcloud.py
@@ -12,7 +12,6 @@ from .common import (
)
from ..compat import (
compat_HTTPError,
- compat_kwargs,
compat_str,
)
from ..utils import (
@@ -96,7 +95,7 @@ class SoundcloudBaseIE(InfoExtractor):
query['client_id'] = self._CLIENT_ID
kwargs['query'] = query
try:
- return super()._download_json(*args, **compat_kwargs(kwargs))
+ return super()._download_json(*args, **kwargs)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 403):
self._store_client_id(None)
diff --git a/yt_dlp/extractor/udemy.py b/yt_dlp/extractor/udemy.py
index 235f89713..77485247f 100644
--- a/yt_dlp/extractor/udemy.py
+++ b/yt_dlp/extractor/udemy.py
@@ -5,7 +5,6 @@ import re
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
- compat_kwargs,
compat_str,
compat_urllib_request,
compat_urlparse,
@@ -132,7 +131,7 @@ class UdemyIE(InfoExtractor):
headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.109 Safari/537.36'
kwargs['headers'] = headers
ret = super(UdemyIE, self)._download_webpage_handle(
- *args, **compat_kwargs(kwargs))
+ *args, **kwargs)
if not ret:
return ret
webpage, _ = ret
diff --git a/yt_dlp/extractor/vimeo.py b/yt_dlp/extractor/vimeo.py
index 972fb480b..a00b387f3 100644
--- a/yt_dlp/extractor/vimeo.py
+++ b/yt_dlp/extractor/vimeo.py
@@ -8,7 +8,6 @@ import itertools
from .common import InfoExtractor
from ..compat import (
- compat_kwargs,
compat_HTTPError,
compat_str,
compat_urlparse,
@@ -109,7 +108,7 @@ class VimeoBaseInfoExtractor(InfoExtractor):
def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
vimeo_config = self._search_regex(
r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));',
- webpage, 'vimeo config', *args, **compat_kwargs(kwargs))
+ webpage, 'vimeo config', *args, **kwargs)
if vimeo_config:
return self._parse_json(vimeo_config, video_id)
generated by cgit v1.2.3 (git 2.25.1) at 2025-07-30 17:18:11 +0000