[egghead] Fix extraction (closes #14388)

This commit is contained in:
Sergey M․ 2017-10-29 07:11:37 +07:00
parent 9211e3319e
commit 514e8aefd4
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D

View File

@ -2,7 +2,9 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
determine_ext,
int_or_none,
try_get,
unified_timestamp,
@ -17,7 +19,7 @@ class EggheadCourseIE(InfoExtractor):
'url': 'https://egghead.io/courses/professor-frisby-introduces-composable-functional-javascript',
'playlist_count': 29,
'info_dict': {
'id': 'professor-frisby-introduces-composable-functional-javascript',
'id': '72',
'title': 'Professor Frisby Introduces Composable Functional JavaScript',
'description': 're:(?s)^This course teaches the ubiquitous.*You\'ll start composing functionality before you know it.$',
},
@ -26,14 +28,28 @@ class EggheadCourseIE(InfoExtractor):
def _real_extract(self, url):
playlist_id = self._match_id(url)
course = self._download_json(
'https://egghead.io/api/v1/series/%s' % playlist_id, playlist_id)
lessons = self._download_json(
'https://egghead.io/api/v1/series/%s/lessons' % playlist_id,
playlist_id, 'Downloading course lessons JSON')
entries = [
self.url_result(
'wistia:%s' % lesson['wistia_id'], ie='Wistia',
video_id=lesson['wistia_id'], video_title=lesson.get('title'))
for lesson in course['lessons'] if lesson.get('wistia_id')]
entries = []
for lesson in lessons:
lesson_url = lesson.get('http_url')
if not lesson_url or not isinstance(lesson_url, compat_str):
continue
lesson_id = lesson.get('id')
if lesson_id:
lesson_id = compat_str(lesson_id)
entries.append(self.url_result(
lesson_url, ie=EggheadLessonIE.ie_key(), video_id=lesson_id))
course = self._download_json(
'https://egghead.io/api/v1/series/%s' % playlist_id,
playlist_id, 'Downloading course JSON', fatal=False) or {}
playlist_id = course.get('id')
if playlist_id:
playlist_id = compat_str(playlist_id)
return self.playlist_result(
entries, playlist_id, course.get('title'),
@ -43,11 +59,12 @@ def _real_extract(self, url):
class EggheadLessonIE(InfoExtractor):
IE_DESC = 'egghead.io lesson'
IE_NAME = 'egghead:lesson'
_VALID_URL = r'https://egghead\.io/lessons/(?P<id>[^/?#&]+)'
_TEST = {
_VALID_URL = r'https://egghead\.io/(?:api/v1/)?lessons/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://egghead.io/lessons/javascript-linear-data-flow-with-container-style-types-box',
'info_dict': {
'id': 'fv5yotjxcg',
'id': '1196',
'display_id': 'javascript-linear-data-flow-with-container-style-types-box',
'ext': 'mp4',
'title': 'Create linear data flow with container style types (Box)',
'description': 'md5:9aa2cdb6f9878ed4c39ec09e85a8150e',
@ -60,25 +77,51 @@ class EggheadLessonIE(InfoExtractor):
},
'params': {
'skip_download': True,
'format': 'bestvideo',
},
}
}, {
'url': 'https://egghead.io/api/v1/lessons/react-add-redux-to-a-react-application',
'only_matching': True,
}]
def _real_extract(self, url):
lesson_id = self._match_id(url)
display_id = self._match_id(url)
lesson = self._download_json(
'https://egghead.io/api/v1/lessons/%s' % lesson_id, lesson_id)
'https://egghead.io/api/v1/lessons/%s' % display_id, display_id)
lesson_id = compat_str(lesson['id'])
title = lesson['title']
formats = []
for _, format_url in lesson['media_urls'].items():
if not format_url or not isinstance(format_url, compat_str):
continue
ext = determine_ext(format_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
format_url, lesson_id, 'mp4', entry_protocol='m3u8',
m3u8_id='hls', fatal=False))
elif ext == 'mpd':
formats.extend(self._extract_mpd_formats(
format_url, lesson_id, mpd_id='dash', fatal=False))
else:
formats.append({
'url': format_url,
})
self._sort_formats(formats)
return {
'_type': 'url_transparent',
'ie_key': 'Wistia',
'url': 'wistia:%s' % lesson['wistia_id'],
'id': lesson['wistia_id'],
'title': lesson.get('title'),
'id': lesson_id,
'display_id': display_id,
'title': title,
'description': lesson.get('summary'),
'thumbnail': lesson.get('thumb_nail'),
'timestamp': unified_timestamp(lesson.get('published_at')),
'duration': int_or_none(lesson.get('duration')),
'view_count': int_or_none(lesson.get('plays_count')),
'tags': try_get(lesson, lambda x: x['tag_list'], list),
'series': try_get(
lesson, lambda x: x['series']['title'], compat_str),
'formats': formats,
}