1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-12-05 14:47:55 +01:00
youtube-dl/youtube_dl/extractor/wsj.py

124 lines
4.6 KiB
Python
Raw Normal View History

2016-10-02 13:39:18 +02:00
# coding: utf-8
2015-02-03 10:58:28 +01:00
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
2016-04-29 22:35:09 +02:00
float_or_none,
2015-02-03 10:58:28 +01:00
unified_strdate,
)
class WSJIE(InfoExtractor):
2017-03-26 00:47:48 +01:00
_VALID_URL = r'''(?x)
(?:
https?://video-api\.wsj\.com/api-video/player/iframe\.html\?.*?\bguid=|
https?://(?:www\.)?(?:wsj|barrons)\.com/video/(?:[^/]+/)+|
wsj:
)
(?P<id>[a-fA-F0-9-]{36})
'''
2015-02-03 10:58:28 +01:00
IE_DESC = 'Wall Street Journal'
2016-04-29 22:35:09 +02:00
_TESTS = [{
2015-02-03 10:58:28 +01:00
'url': 'http://video-api.wsj.com/api-video/player/iframe.html?guid=1BD01A4C-BFE8-40A5-A42F-8A8AF9898B1A',
2016-04-29 22:35:09 +02:00
'md5': 'e230a5bb249075e40793b655a54a02e4',
2015-02-03 10:58:28 +01:00
'info_dict': {
'id': '1BD01A4C-BFE8-40A5-A42F-8A8AF9898B1A',
'ext': 'mp4',
'upload_date': '20150202',
2015-02-18 19:56:24 +01:00
'uploader_id': 'jdesai',
'creator': 'jdesai',
2015-02-03 10:58:28 +01:00
'categories': list, # a long list
'duration': 90,
'title': 'Bills Coach Rex Ryan Updates His Old Jets Tattoo',
},
2016-04-29 22:35:09 +02:00
}, {
'url': 'http://www.wsj.com/video/can-alphabet-build-a-smarter-city/359DDAA8-9AC1-489C-82E6-0429C1E430E0.html',
'only_matching': True,
}, {
'url': 'http://www.barrons.com/video/capitalism-deserves-more-respect-from-millennials/F301217E-6F46-43AE-B8D2-B7180D642EE9.html',
'only_matching': True,
}, {
'url': 'https://www.wsj.com/video/series/a-brief-history-of/the-modern-cell-carrier-how-we-got-here/980E2187-401D-48A1-B82B-1486CEE06CB9',
'only_matching': True,
2016-04-29 22:35:09 +02:00
}]
2015-02-03 10:58:28 +01:00
def _real_extract(self, url):
video_id = self._match_id(url)
info = self._download_json(
'http://video-api.wsj.com/api-video/find_all_videos.asp', video_id,
query={
'type': 'guid',
'count': 1,
'query': video_id,
'fields': ','.join((
'type', 'hls', 'videoMP4List', 'thumbnailList', 'author',
'description', 'name', 'duration', 'videoURL', 'titletag',
'formattedCreationDate', 'keywords', 'editor')),
})['items'][0]
2015-02-03 10:58:28 +01:00
title = info.get('name', info.get('titletag'))
2016-04-29 22:35:09 +02:00
formats = []
f4m_url = info.get('videoURL')
if f4m_url:
formats.extend(self._extract_f4m_formats(
f4m_url, video_id, f4m_id='hds', fatal=False))
m3u8_url = info.get('hls')
if m3u8_url:
2015-02-03 10:58:28 +01:00
formats.extend(self._extract_m3u8_formats(
info['hls'], video_id, ext='mp4',
2016-04-29 22:35:09 +02:00
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
for v in info.get('videoMP4List', []):
mp4_url = v.get('url')
if not mp4_url:
continue
tbr = int_or_none(v.get('bitrate'))
formats.append({
'url': mp4_url,
'format_id': 'http' + ('-%d' % tbr if tbr else ''),
'tbr': tbr,
'width': int_or_none(v.get('width')),
'height': int_or_none(v.get('height')),
'fps': float_or_none(v.get('fps')),
})
2015-02-03 10:58:28 +01:00
self._sort_formats(formats)
return {
'id': video_id,
'formats': formats,
2016-04-29 22:35:09 +02:00
# Thumbnails are conveniently in the correct format already
'thumbnails': info.get('thumbnailList'),
'creator': info.get('author'),
'uploader_id': info.get('editor'),
'duration': int_or_none(info.get('duration')),
'upload_date': unified_strdate(info.get(
'formattedCreationDate'), day_first=False),
2015-02-03 10:58:28 +01:00
'title': title,
2016-04-29 22:35:09 +02:00
'categories': info.get('keywords'),
2015-02-03 10:58:28 +01:00
}
2017-03-26 00:47:48 +01:00
class WSJArticleIE(InfoExtractor):
_VALID_URL = r'(?i)https?://(?:www\.)?wsj\.com/articles/(?P<id>[^/?#&]+)'
_TEST = {
2017-03-26 00:47:48 +01:00
'url': 'https://www.wsj.com/articles/dont-like-china-no-pandas-for-you-1490366939?',
'info_dict': {
'id': '4B13FA62-1D8C-45DB-8EA1-4105CB20B362',
'ext': 'mp4',
'upload_date': '20170221',
'uploader_id': 'ralcaraz',
'title': 'Bao Bao the Panda Leaves for China',
}
}
2017-03-26 00:47:48 +01:00
def _real_extract(self, url):
article_id = self._match_id(url)
webpage = self._download_webpage(url, article_id)
video_id = self._search_regex(
r'data-src=["\']([a-fA-F0-9-]{36})', webpage, 'video id')
2017-03-26 00:47:48 +01:00
return self.url_result('wsj:%s' % video_id, WSJIE.ie_key(), video_id)