Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-29 19:47:54 +01:00
Code Issues Releases 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

29
youtube_dl/extractor/alura.py
View File

@ -29,27 +29,24 @@ class AluraIE(InfoExtractor):
'id': '60095', 'id': '60095',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Referências, ref-set e alter' 'title': 'Referências, ref-set e alter'
},
'skip': 'Requires alura account credentials',
}, },
'skip': 'Requires alura account credentials'},
{ {
# URL without video # URL without video
'url': 'https://cursos.alura.com.br/course/clojure-mutabilidade-com-atoms-e-refs/task/60098', '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', 'url': 'https://cursos.alura.com.br/course/fundamentos-market-digital/task/55219',
'only_matching': True, 'only_matching': True}
}
] ]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
course = self._search_regex(self._VALID_URL, url, 'post url', group='course_name') course = self._search_regex(self._VALID_URL, url, 'post url', group='course_name')
video_url = self._VIDEO_URL % (course,video_id) video_url = self._VIDEO_URL % (course, video_id)
video_dict = self._download_json(video_url, None, 'Searching for videos', expected_status=[404,500]) video_dict = self._download_json(video_url, None, 'Searching for videos', expected_status=[404, 500])
if video_dict: if video_dict:
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
@ -152,9 +149,21 @@ class AluraCourseIE(AluraIE):
page_url = urljoin(url, path) page_url = urljoin(url, path)
section_path = self._download_webpage(page_url, course_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): 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 = clean_html(
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')) 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) video_url = urljoin(url, path_video)
entry = { entry = {
'_type': 'url_transparent', '_type': 'url_transparent',
'id': self._match_id(video_url), 'id': self._match_id(video_url),