From c701472fc99c90f6ef4fdf0f0169a342f2e9e892 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 7 Apr 2019 02:15:25 +0700 Subject: [PATCH] [platzi] Add extractor (closes #20562) --- youtube_dl/extractor/extractors.py | 4 + youtube_dl/extractor/platzi.py | 217 +++++++++++++++++++++++++++++ 2 files changed, 221 insertions(+) create mode 100644 youtube_dl/extractor/platzi.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 01119f2bb..41ab36213 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -868,6 +868,10 @@ from .picarto import ( from .piksel import PikselIE from .pinkbike import PinkbikeIE from .pladform import PladformIE +from .platzi import ( + PlatziIE, + PlatziCourseIE, +) from .playfm import PlayFMIE from .playplustv import PlayPlusTVIE from .plays import PlaysTVIE diff --git a/youtube_dl/extractor/platzi.py b/youtube_dl/extractor/platzi.py new file mode 100644 index 000000000..557b2b5ad --- /dev/null +++ b/youtube_dl/extractor/platzi.py @@ -0,0 +1,217 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import ( + compat_b64decode, + compat_str, +) +from ..utils import ( + clean_html, + ExtractorError, + int_or_none, + str_or_none, + try_get, + url_or_none, + urlencode_postdata, + urljoin, +) + + +class PlatziIE(InfoExtractor): + _VALID_URL = r'''(?x) + https?:// + (?: + platzi\.com/clases| # es version + courses\.platzi\.com/classes # en version + )/[^/]+/(?P\d+)-[^/?\#&]+ + ''' + _LOGIN_URL = 'https://platzi.com/login/' + _NETRC_MACHINE = 'platzi' + + _TESTS = [{ + 'url': 'https://platzi.com/clases/1311-next-js/12074-creando-nuestra-primera-pagina/', + 'md5': '8f56448241005b561c10f11a595b37e3', + 'info_dict': { + 'id': '12074', + 'ext': 'mp4', + 'title': 'Creando nuestra primera página', + 'description': 'md5:4c866e45034fc76412fbf6e60ae008bc', + 'duration': 420, + }, + 'skip': 'Requires platzi account credentials', + }, { + 'url': 'https://courses.platzi.com/classes/1367-communication-codestream/13430-background/', + 'info_dict': { + 'id': '13430', + 'ext': 'mp4', + 'title': 'Background', + 'description': 'md5:49c83c09404b15e6e71defaf87f6b305', + 'duration': 360, + }, + 'skip': 'Requires platzi account credentials', + 'params': { + 'skip_download': True, + }, + }] + + def _real_initialize(self): + self._login() + + def _login(self): + username, password = self._get_login_info() + if username is None: + return + + login_page = self._download_webpage( + self._LOGIN_URL, None, 'Downloading login page') + + login_form = self._hidden_inputs(login_page) + + login_form.update({ + 'email': username, + 'password': password, + }) + + urlh = self._request_webpage( + self._LOGIN_URL, None, 'Logging in', + data=urlencode_postdata(login_form), + headers={'Referer': self._LOGIN_URL}) + + # login succeeded + if 'platzi.com/login' not in compat_str(urlh.geturl()): + return + + login_error = self._webpage_read_content( + urlh, self._LOGIN_URL, None, 'Downloading login error page') + + login = self._parse_json( + self._search_regex( + r'login\s*=\s*({.+?})(?:\s*;|\s*[^/?\#&]+) + ''' + _TESTS = [{ + 'url': 'https://platzi.com/clases/next-js/', + 'info_dict': { + 'id': '1311', + 'title': 'Curso de Next.js', + }, + 'playlist_count': 22, + }, { + 'url': 'https://courses.platzi.com/classes/communication-codestream/', + 'info_dict': { + 'id': '1367', + 'title': 'Codestream Course', + }, + 'playlist_count': 14, + }] + + @classmethod + def suitable(cls, url): + return False if PlatziIE.suitable(url) else super(PlatziCourseIE, cls).suitable(url) + + def _real_extract(self, url): + course_name = self._match_id(url) + + webpage = self._download_webpage(url, course_name) + + props = self._parse_json( + self._search_regex(r'data\s*=\s*({.+?})\s*;', webpage, 'data'), + course_name)['initialProps'] + + entries = [] + for chapter_num, chapter in enumerate(props['concepts'], 1): + if not isinstance(chapter, dict): + continue + materials = chapter.get('materials') + if not materials or not isinstance(materials, list): + continue + chapter_title = chapter.get('title') + chapter_id = str_or_none(chapter.get('id')) + for material in materials: + if not isinstance(material, dict): + continue + if material.get('material_type') != 'video': + continue + video_url = urljoin(url, material.get('url')) + if not video_url: + continue + entries.append({ + '_type': 'url_transparent', + 'url': video_url, + 'title': str_or_none(material.get('name')), + 'id': str_or_none(material.get('id')), + 'ie_key': PlatziIE.ie_key(), + 'chapter': chapter_title, + 'chapter_number': chapter_num, + 'chapter_id': chapter_id, + }) + + course_id = compat_str(try_get(props, lambda x: x['course']['id'])) + course_title = try_get(props, lambda x: x['course']['name'], compat_str) + + return self.playlist_result(entries, course_id, course_title)