From 300a9da662dca1441eeab0330f02a85c21f46f0c Mon Sep 17 00:00:00 2001
From: uno20001 <>
Date: Sat, 2 Nov 2019 16:25:27 +0100
Subject: [PATCH 1/3] [youtube_dl/utils] add support for octal escape sequences
to js_to_json()
---
youtube_dl/utils.py | 15 ++++++++++++---
1 file changed, 12 insertions(+), 3 deletions(-)
diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index aed988b88..85fe1e34a 100644
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -3979,18 +3979,27 @@ def js_to_json(code):
def fix_kv(m):
v = m.group(0)
+
if v in ('true', 'false', 'null'):
return v
elif v.startswith('/*') or v.startswith('//') or v == ',':
return ""
if v[0] in ("'", '"'):
+
+ v = v[1:-1]
+
+ # convert Javascript's octal escape sequences (and '\0')
+ # into valid JSON escape sequences ( e.g '\347' => '\u00e7', '\0' => '\u0000' )
+ # regex based on https://mathiasbynens.be/notes/javascript-escapes
+ v = re.sub(r'\\([0-7]{1,3})', lambda x: "\\u%04x" % int(x.group(1), 8), v)
+
v = re.sub(r'(?s)\\.|"', lambda m: {
'"': '\\"',
"\\'": "'",
'\\\n': '',
'\\x': '\\u00',
- }.get(m.group(0), m.group(0)), v[1:-1])
+ }.get(m.group(0), m.group(0)), v)
for regex, base in INTEGER_TABLE:
im = re.match(regex, v)
@@ -4001,8 +4010,8 @@ def js_to_json(code):
return '"%s"' % v
return re.sub(r'''(?sx)
- "(?:[^"\\]*(?:\\\\|\\['"nurtbfx/\n]))*[^"\\]*"|
- '(?:[^'\\]*(?:\\\\|\\['"nurtbfx/\n]))*[^'\\]*'|
+ "(?:[^"\\]*(?:\\\\|\\['"nurtbfx/\n]?))*[^"\\]*"|
+ '(?:[^'\\]*(?:\\\\|\\['"nurtbfx/\n]?))*[^'\\]*'|
{comment}|,(?={skip}[\]}}])|
(?:(?<![0-9])[eE]|[a-df-zA-DF-Z_])[.a-zA-Z_0-9]*|
\b(?:0[xX][0-9a-fA-F]+|0+[0-7]+)(?:{skip}:)?|
From b812fcee81e707eaeba2fe2353033887f52e409f Mon Sep 17 00:00:00 2001
From: uno20001 <>
Date: Sat, 2 Nov 2019 16:25:58 +0100
Subject: [PATCH 2/3] [EnseignerTV5Monde] new extractor (closes #22851)
---
youtube_dl/extractor/enseignertv5monde.py | 44 +++++++++++++++++++++++
youtube_dl/extractor/extractors.py | 1 +
2 files changed, 45 insertions(+)
create mode 100644 youtube_dl/extractor/enseignertv5monde.py
diff --git a/youtube_dl/extractor/enseignertv5monde.py b/youtube_dl/extractor/enseignertv5monde.py
new file mode 100644
index 000000000..a08632dd9
--- /dev/null
+++ b/youtube_dl/extractor/enseignertv5monde.py
@@ -0,0 +1,44 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import unified_strdate
+
+
+class EnseignerTV5MondeIE(InfoExtractor):
+ _VALID_URL = r'https?:\/\/(?:www\.)?enseigner\.tv5monde\.com\/videos-sans-fiche\/(?P<id>[a-zA-Z0-9\-]+)'
+ _TESTS = [
+ {
+ 'url': 'https://enseigner.tv5monde.com/videos-sans-fiche/la-culture-en-france',
+ 'md5': 'bb9e4c4701c1873a3790a0a33eb89ce6',
+ 'info_dict': {
+ 'id': 'la-culture-en-france',
+ 'ext': 'mp4',
+ 'title': 'La culture en France',
+ 'thumbnail': r're:^https?://.*\.jpg$',
+ }
+ },
+ {
+ 'url': 'https://enseigner.tv5monde.com/videos-sans-fiche/les-chapeaux-de-la-maison-michel',
+ 'md5': 'bdfc21506aee0ffa2afd823f1c44ce66',
+ 'info_dict': {
+ 'id': 'les-chapeaux-de-la-maison-michel',
+ 'ext': 'mp4',
+ 'title': 'Les chapeaux de la Maison Michel',
+ 'thumbnail': r're:^https?://.*\.jpg$',
+ }
+ }
+ ]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+
+ d = self._extract_jwplayer_data(webpage, video_id, require_title=False)
+
+ d.update({
+ 'title': self._og_search_title(webpage),
+ 'thumbnail': self._og_search_thumbnail(webpage),
+ 'release_date': unified_strdate(self._html_search_regex(r'itemprop="datePublished"[^>]*>([0-9/]+)</time>', webpage, 'release date', fatal=False))})
+
+ return d
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index af3fff601..06c546add 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -321,6 +321,7 @@ from .ellentube import (
from .elpais import ElPaisIE
from .embedly import EmbedlyIE
from .engadget import EngadgetIE
+from .enseignertv5monde import EnseignerTV5MondeIE
from .eporner import EpornerIE
from .eroprofile import EroProfileIE
from .escapist import EscapistIE
From 1ebe09fb349a70954347d85f6aa2fcb4d0e0f3ad Mon Sep 17 00:00:00 2001
From: uno20001 <>
Date: Sat, 2 Nov 2019 20:47:40 +0100
Subject: [PATCH 3/3] [youtube_dl/utils] fix failed test
---
youtube_dl/utils.py | 32 ++++++++++++++++++--------------
1 file changed, 18 insertions(+), 14 deletions(-)
diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index 85fe1e34a..0cb410ac7 100644
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -3976,6 +3976,23 @@ def js_to_json(code):
(r'(?s)^(0[xX][0-9a-fA-F]+){skip}:?$'.format(skip=SKIP_RE), 16),
(r'(?s)^(0+[0-7]+){skip}:?$'.format(skip=SKIP_RE), 8),
)
+
+ def convert_escapes(m):
+ # convert Javascript's octal escape sequences (and '\0')
+ # into valid JSON escape sequences ( e.g '\347' => '\u00e7', '\0' => '\u0000'
+ if m.group(1):
+ return "\\u%04x" % int(m.group(1), 8)
+
+ # convert the remaining escape sequences
+ # into valid JSON
+ return {
+ '"': '\\"',
+ "\\'": "'",
+ '\\\n': '',
+ '\\x': '\\u00',
+ }.get(m.group(0), m.group(0))
+
+
def fix_kv(m):
v = m.group(0)
@@ -3986,20 +4003,7 @@ def js_to_json(code):
return ""
if v[0] in ("'", '"'):
-
- v = v[1:-1]
-
- # convert Javascript's octal escape sequences (and '\0')
- # into valid JSON escape sequences ( e.g '\347' => '\u00e7', '\0' => '\u0000' )
- # regex based on https://mathiasbynens.be/notes/javascript-escapes
- v = re.sub(r'\\([0-7]{1,3})', lambda x: "\\u%04x" % int(x.group(1), 8), v)
-
- v = re.sub(r'(?s)\\.|"', lambda m: {
- '"': '\\"',
- "\\'": "'",
- '\\\n': '',
- '\\x': '\\u00',
- }.get(m.group(0), m.group(0)), v)
+ v = re.sub(r'(?s)\\(?:([0-7]{1,3})|.)|"', convert_escapes, v[1:-1])
for regex, base in INTEGER_TABLE:
im = re.match(regex, v)