external/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-13 02:14:20 +01:00
Code Issues Projects Releases Packages Wiki Activity

- formatting

Browse source
This commit is contained in:
Hugo Alves De Azevedo 2020-08-28 14:25:37 -03:00
parent 2adf91f94f
commit 39672cdc79
1 changed files with 20 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

25
youtube_dl/extractor/alura.py
View file

@ -30,17 +30,14 @@ class AluraIE(InfoExtractor):
'ext': 'mp4',
'title': 'Referências, ref-set e alter'
},
'skip': 'Requires alura account credentials',
},
'skip': 'Requires alura account credentials'},
{
# URL without video
'url': 'https://cursos.alura.com.br/course/clojure-mutabilidade-com-atoms-e-refs/task/60098',
'only_matching': True,
},
'only_matching': True},
{
'url': 'https://cursos.alura.com.br/course/fundamentos-market-digital/task/55219',
'only_matching': True,
}
'only_matching': True}
]
def _real_extract(self, url):
@ -152,9 +149,21 @@ def _real_extract(self, url):
page_url = urljoin(url, path)
section_path = self._download_webpage(page_url, course_path)
for path_video in re.findall(r'<a\b(?=[^>]* class="[^"]*(?<=[" ])task-menu-nav-item-link-VIDEO[" ])(?=[^>]* href="([^"]*))', section_path):
chapter = clean_html(self._search_regex(r'<h3[^>]+class=(["\'])task-menu-section-title-text\1[^>]*>(?P<chapter>[^<]+)',section_path, 'chapter', group='chapter'))
chapter_number = int_or_none(self._search_regex(r'<span[^>]+class=(["\'])task-menu-section-title-number[^>]*>(.*?)<strong>(?P<chapter_number>[^<]+)</strong>',section_path, 'chapter number', group='chapter_number'))
chapter = clean_html(
self._search_regex(
r'<h3[^>]+class=(["\'])task-menu-section-title-text\1[^>]*>(?P<chapter>[^<]+)',
section_path,
'chapter',
group='chapter'))
chapter_number = int_or_none(
self._search_regex(
r'<span[^>]+class=(["\'])task-menu-section-title-number[^>]*>(.*?)<strong>(?P<chapter_number>[^<]+)</strong>',
section_path,
'chapter number',
group='chapter_number'))
video_url = urljoin(url, path_video)
entry = {
'_type': 'url_transparent',
'id': self._match_id(video_url),