yt-dlp/yt_dlp/extractor/alura.py

164 lines
6.3 KiB
Python
Raw Normal View History

2020-08-26 01:39:20 +00:00
import re
import urllib.parse
2020-08-26 01:39:20 +00:00
from .common import InfoExtractor
from ..utils import (
ExtractorError,
clean_html,
int_or_none,
2020-08-26 01:39:20 +00:00
urlencode_postdata,
2020-08-28 13:02:31 +00:00
urljoin,
2020-08-26 01:39:20 +00:00
)
class AluraIE(InfoExtractor):
_VALID_URL = r'https?://(?:cursos\.)?alura\.com\.br/course/(?P<course_name>[^/]+)/task/(?P<id>\d+)'
_LOGIN_URL = 'https://cursos.alura.com.br/loginForm?urlAfterLogin=/loginForm'
_VIDEO_URL = 'https://cursos.alura.com.br/course/%s/task/%s/video'
2020-08-28 13:02:31 +00:00
_NETRC_MACHINE = 'alura'
_TESTS = [{
'url': 'https://cursos.alura.com.br/course/clojure-mutabilidade-com-atoms-e-refs/task/60095',
2020-08-26 01:39:20 +00:00
'info_dict': {
2020-08-28 13:02:31 +00:00
'id': '60095',
2020-08-26 01:39:20 +00:00
'ext': 'mp4',
'title': 'Referências, ref-set e alter',
2020-08-28 13:02:31 +00:00
},
2020-08-28 17:25:37 +00:00
'skip': 'Requires alura account credentials'},
2020-08-28 13:02:31 +00:00
{
# URL without video
'url': 'https://cursos.alura.com.br/course/clojure-mutabilidade-com-atoms-e-refs/task/60098',
2020-08-28 17:25:37 +00:00
'only_matching': True},
2020-08-28 13:02:31 +00:00
{
'url': 'https://cursos.alura.com.br/course/fundamentos-market-digital/task/55219',
'only_matching': True},
2020-08-28 13:02:31 +00:00
]
2020-08-26 01:39:20 +00:00
def _real_extract(self, url):
course, video_id = self._match_valid_url(url).group('course_name', 'id')
2020-08-28 17:25:37 +00:00
video_url = self._VIDEO_URL % (course, video_id)
2020-08-26 01:39:20 +00:00
2020-08-28 17:40:03 +00:00
video_dict = self._download_json(video_url, video_id, 'Searching for videos')
2020-08-26 01:39:20 +00:00
if video_dict:
webpage = self._download_webpage(url, video_id)
2020-08-28 13:02:31 +00:00
video_title = clean_html(self._search_regex(
2020-08-26 01:39:20 +00:00
r'<span[^>]+class=(["\'])task-body-header-title-text\1[^>]*>(?P<title>[^<]+)',
2020-08-28 13:02:31 +00:00
webpage, 'title', group='title'))
2020-08-26 01:39:20 +00:00
formats = []
for video_obj in video_dict:
video_url_m3u8 = video_obj.get('mp4')
2020-08-26 01:39:20 +00:00
video_format = self._extract_m3u8_formats(
video_url_m3u8, None, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False)
2020-08-28 13:02:31 +00:00
for f in video_format:
m = re.search(r'^[\w \W]*-(?P<res>\w*).mp4[\W \w]*', f['url'])
if m:
if not f.get('height'):
f['height'] = int('720' if m.group('res') == 'hd' else '480')
2020-08-26 01:39:20 +00:00
formats.extend(video_format)
return {
'id': video_id,
'title': video_title,
'formats': formats,
2020-08-26 01:39:20 +00:00
}
def _perform_login(self, username, password):
2020-08-26 01:39:20 +00:00
login_page = self._download_webpage(
self._LOGIN_URL, None, 'Downloading login popup')
def is_logged(webpage):
return any(re.search(p, webpage) for p in (
r'href=[\"|\']?/signout[\"|\']',
r'>Logout<'))
# already logged in
if is_logged(login_page):
return
login_form = self._hidden_inputs(login_page)
login_form.update({
'username': username,
'password': password,
})
post_url = self._search_regex(
r'<form[^>]+class=["|\']signin-form["|\'] action=["|\'](?P<url>.+?)["|\']', login_page,
'post url', default=self._LOGIN_URL, group='url')
if not post_url.startswith('http'):
post_url = urllib.parse.urljoin(self._LOGIN_URL, post_url)
2020-08-26 01:39:20 +00:00
2020-08-28 13:02:31 +00:00
response = self._download_webpage(
2020-08-26 01:39:20 +00:00
post_url, None, 'Logging in',
data=urlencode_postdata(login_form),
headers={'Content-Type': 'application/x-www-form-urlencoded'})
2020-08-28 13:02:31 +00:00
if not is_logged(response):
error = self._html_search_regex(
r'(?s)<p[^>]+class="alert-message[^"]*">(.+?)</p>',
response, 'error message', default=None)
if error:
raise ExtractorError(f'Unable to login: {error}', expected=True)
2020-08-28 13:02:31 +00:00
raise ExtractorError('Unable to log in')
2022-11-16 00:57:43 +00:00
class AluraCourseIE(AluraIE): # XXX: Do not subclass from concrete IE
2020-08-28 13:02:31 +00:00
_VALID_URL = r'https?://(?:cursos\.)?alura\.com\.br/course/(?P<id>[^/]+)'
_LOGIN_URL = 'https://cursos.alura.com.br/loginForm?urlAfterLogin=/loginForm'
_NETRC_MACHINE = 'aluracourse'
_TESTS = [{
'url': 'https://cursos.alura.com.br/course/clojure-mutabilidade-com-atoms-e-refs',
'only_matching': True,
}]
2020-08-28 18:21:52 +00:00
@classmethod
def suitable(cls, url):
return False if AluraIE.suitable(url) else super().suitable(url)
2020-08-28 18:21:52 +00:00
2020-08-28 13:02:31 +00:00
def _real_extract(self, url):
2020-08-26 01:39:20 +00:00
2020-08-28 13:02:31 +00:00
course_path = self._match_id(url)
webpage = self._download_webpage(url, course_path)
course_title = self._search_regex(
r'<h1.*?>(.*?)<strong>(?P<course_title>.*?)</strong></h[0-9]>', webpage,
'course title', default=course_path, group='course_title')
entries = []
if webpage:
for path in re.findall(r'<a\b(?=[^>]* class="[^"]*(?<=[" ])courseSectionList-section[" ])(?=[^>]* href="([^"]*))', webpage):
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):
2020-08-28 17:25:37 +00:00
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'))
2020-08-28 13:02:31 +00:00
video_url = urljoin(url, path_video)
2020-08-28 17:25:37 +00:00
2020-08-28 13:02:31 +00:00
entry = {
'_type': 'url_transparent',
'id': self._match_id(video_url),
'url': video_url,
'id_key': self.ie_key(),
'chapter': chapter,
'chapter_number': chapter_number,
2020-08-28 13:02:31 +00:00
}
entries.append(entry)
2020-08-28 17:25:37 +00:00
return self.playlist_result(entries, course_path, course_title)