aboutsummaryrefslogtreecommitdiffstats
path: root/youtube_dl
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl')
-rw-r--r--youtube_dl/extractor/ctsnews.py49
-rw-r--r--youtube_dl/extractor/extractors.py1
-rw-r--r--youtube_dl/extractor/uol.py128
-rw-r--r--youtube_dl/utils.py1
-rw-r--r--youtube_dl/version.py2
5 files changed, 152 insertions, 29 deletions
diff --git a/youtube_dl/extractor/ctsnews.py b/youtube_dl/extractor/ctsnews.py
index 1622fc844..83ca90c3b 100644
--- a/youtube_dl/extractor/ctsnews.py
+++ b/youtube_dl/extractor/ctsnews.py
@@ -1,13 +1,12 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
-from ..utils import parse_iso8601, ExtractorError
+from ..utils import unified_timestamp
class CtsNewsIE(InfoExtractor):
IE_DESC = '華視新聞'
- # https connection failed (Connection reset)
_VALID_URL = r'https?://news\.cts\.com\.tw/[a-z]+/[a-z]+/\d+/(?P<id>\d+)\.html'
_TESTS = [{
'url': 'http://news.cts.com.tw/cts/international/201501/201501291578109.html',
@@ -16,7 +15,7 @@ class CtsNewsIE(InfoExtractor):
'id': '201501291578109',
'ext': 'mp4',
'title': '以色列.真主黨交火 3人死亡',
- 'description': 'md5:95e9b295c898b7ff294f09d450178d7d',
+ 'description': '以色列和黎巴嫩真主黨，爆發五年最嚴重衝突，雙方砲轟交火，兩名以軍死亡，還有一名西班牙籍的聯合國維和人...',
'timestamp': 1422528540,
'upload_date': '20150129',
}
@@ -28,7 +27,7 @@ class CtsNewsIE(InfoExtractor):
'id': '201309031304098',
'ext': 'mp4',
'title': '韓國31歲童顏男 貌如十多歲小孩',
- 'description': 'md5:f183feeba3752b683827aab71adad584',
+ 'description': '越有年紀的人，越希望看起來年輕一點，而南韓卻有一位31歲的男子，看起來像是11、12歲的小孩，身...',
'thumbnail': 're:^https?://.*\.jpg$',
'timestamp': 1378205880,
'upload_date': '20130903',
@@ -36,8 +35,7 @@ class CtsNewsIE(InfoExtractor):
}, {
# With Youtube embedded video
'url': 'http://news.cts.com.tw/cts/money/201501/201501291578003.html',
- 'md5': '1d842c771dc94c8c3bca5af2cc1db9c5',
- 'add_ie': ['Youtube'],
+ 'md5': 'e4726b2ccd70ba2c319865e28f0a91d1',
'info_dict': {
'id': 'OVbfO7d0_hQ',
'ext': 'mp4',
@@ -47,42 +45,37 @@ class CtsNewsIE(InfoExtractor):
'upload_date': '20150128',
'uploader_id': 'TBSCTS',
'uploader': '中華電視公司',
- }
+ },
+ 'add_ie': ['Youtube'],
}]
def _real_extract(self, url):
news_id = self._match_id(url)
page = self._download_webpage(url, news_id)
- if self._search_regex(r'(CTSPlayer2)', page, 'CTSPlayer2 identifier', default=None):
- feed_url = self._html_search_regex(
- r'(http://news\.cts\.com\.tw/action/mp4feed\.php\?news_id=\d+)',
- page, 'feed url')
- video_url = self._download_webpage(
- feed_url, news_id, note='Fetching feed')
+ news_id = self._hidden_inputs(page).get('get_id')
+
+ if news_id:
+ mp4_feed = self._download_json(
+ 'http://news.cts.com.tw/action/test_mp4feed.php',
+ news_id, note='Fetching feed', query={'news_id': news_id})
+ video_url = mp4_feed['source_url']
else:
self.to_screen('Not CTSPlayer video, trying Youtube...')
youtube_url = self._search_regex(
- r'src="(//www\.youtube\.com/embed/[^"]+)"', page, 'youtube url',
- default=None)
- if not youtube_url:
- raise ExtractorError('The news includes no videos!', expected=True)
+ r'src="(//www\.youtube\.com/embed/[^"]+)"', page, 'youtube url')
- return {
- '_type': 'url',
- 'url': youtube_url,
- 'ie_key': 'Youtube',
- }
+ return self.url_result(youtube_url, ie='Youtube')
description = self._html_search_meta('description', page)
- title = self._html_search_meta('title', page)
+ title = self._html_search_meta('title', page, fatal=True)
thumbnail = self._html_search_meta('image', page)
datetime_str = self._html_search_regex(
- r'(\d{4}/\d{2}/\d{2} \d{2}:\d{2})', page, 'date and time')
- # Transform into ISO 8601 format with timezone info
- datetime_str = datetime_str.replace('/', '-') + ':00+0800'
- timestamp = parse_iso8601(datetime_str, delimiter=' ')
+ r'(\d{4}/\d{2}/\d{2} \d{2}:\d{2})', page, 'date and time', fatal=False)
+ timestamp = None
+ if datetime_str:
+ timestamp = unified_timestamp(datetime_str) - 8 * 3600
return {
'id': news_id,
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index f1043dae6..387230be0 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -929,6 +929,7 @@ from .udemy import (
from .udn import UDNEmbedIE
from .digiteka import DigitekaIE
from .unistra import UnistraIE
+from .uol import UOLIE
from .urort import UrortIE
from .urplay import URPlayIE
from .usatoday import USATodayIE
diff --git a/youtube_dl/extractor/uol.py b/youtube_dl/extractor/uol.py
new file mode 100644
index 000000000..c27c64387
--- /dev/null
+++ b/youtube_dl/extractor/uol.py
@@ -0,0 +1,128 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+ clean_html,
+ int_or_none,
+ parse_duration,
+ update_url_query,
+ str_or_none,
+)
+
+
+class UOLIE(InfoExtractor):
+ IE_NAME = 'uol.com.br'
+ _VALID_URL = r'https?://(?:.+?\.)?uol\.com\.br/.*?(?:(?:mediaId|v)=|view/(?:[a-z0-9]+/)?|video(?:=|/(?:\d{4}/\d{2}/\d{2}/)?))(?P<id>\d+|[\w-]+-[A-Z0-9]+)'
+ _TESTS = [{
+ 'url': 'http://player.mais.uol.com.br/player_video_v3.swf?mediaId=15951931',
+ 'md5': '25291da27dc45e0afb5718a8603d3816',
+ 'info_dict': {
+ 'id': '15951931',
+ 'ext': 'mp4',
+ 'title': 'Miss simpatia é encontrada morta',
+ 'description': 'md5:3f8c11a0c0556d66daf7e5b45ef823b2',
+ }
+ }, {
+ 'url': 'http://tvuol.uol.com.br/video/incendio-destroi-uma-das-maiores-casas-noturnas-de-londres-04024E9A3268D4C95326',
+ 'md5': 'e41a2fb7b7398a3a46b6af37b15c00c9',
+ 'info_dict': {
+ 'id': '15954259',
+ 'ext': 'mp4',
+ 'title': 'Incêndio destrói uma das maiores casas noturnas de Londres',
+ 'description': 'Em Londres, um incêndio destruiu uma das maiores boates da cidade. Não há informações sobre vítimas.',
+ }
+ }, {
+ 'url': 'http://mais.uol.com.br/static/uolplayer/index.html?mediaId=15951931',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://mais.uol.com.br/view/15954259',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://noticias.band.uol.com.br/brasilurgente/video/2016/08/05/15951931/miss-simpatia-e-encontrada-morta.html',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://videos.band.uol.com.br/programa.asp?e=noticias&pr=brasil-urgente&v=15951931&t=Policia-desmonte-base-do-PCC-na-Cracolandia',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://mais.uol.com.br/view/cphaa0gl2x8r/incendio-destroi-uma-das-maiores-casas-noturnas-de-londres-04024E9A3268D4C95326',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://noticias.uol.com.br//videos/assistir.htm?video=rafaela-silva-inspira-criancas-no-judo-04024D983968D4C95326',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://mais.uol.com.br/view/e0qbgxid79uv/15275470',
+ 'only_matching': True,
+ }]
+
+ _FORMATS = {
+ '2': {
+ 'width': 640,
+ 'height': 360,
+ },
+ '5': {
+ 'width': 1080,
+ 'height': 720,
+ },
+ '6': {
+ 'width': 426,
+ 'height': 240,
+ },
+ '7': {
+ 'width': 1920,
+ 'height': 1080,
+ },
+ '8': {
+ 'width': 192,
+ 'height': 144,
+ },
+ '9': {
+ 'width': 568,
+ 'height': 320,
+ },
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ if not video_id.isdigit():
+ embed_page = self._download_webpage('https://jsuol.com.br/c/tv/uol/embed/?params=[embed,%s]' % video_id, video_id)
+ video_id = self._search_regex(r'mediaId=(\d+)', embed_page, 'media id')
+ video_data = self._download_json(
+ 'http://mais.uol.com.br/apiuol/v3/player/getMedia/%s.json' % video_id,
+ video_id)['item']
+ title = video_data['title']
+
+ query = {
+ 'ver': video_data.get('numRevision', 2),
+ 'r': 'http://mais.uol.com.br',
+ }
+ formats = []
+ for f in video_data.get('formats', []):
+ f_url = f.get('url') or f.get('secureUrl')
+ if not f_url:
+ continue
+ format_id = str_or_none(f.get('id'))
+ fmt = {
+ 'format_id': format_id,
+ 'url': update_url_query(f_url, query),
+ }
+ fmt.update(self._FORMATS.get(format_id, {}))
+ formats.append(fmt)
+ self._sort_formats(formats)
+
+ tags = []
+ for tag in video_data.get('tags', []):
+ tag_description = tag.get('description')
+ if not tag_description:
+ continue
+ tags.append(tag_description)
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'description': clean_html(video_data.get('desMedia')),
+ 'thumbnail': video_data.get('thumbnail'),
+ 'duration': int_or_none(video_data.get('durationSeconds')) or parse_duration(video_data.get('duration')),
+ 'tags': tags,
+ 'formats': formats,
+ }
diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index c50238ba1..a03f7184d 100644
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -122,6 +122,7 @@ DATE_FORMATS = (
'%Y %m %d',
'%Y-%m-%d',
'%Y/%m/%d',
+ '%Y/%m/%d %H:%M',
'%Y/%m/%d %H:%M:%S',
'%Y-%m-%d %H:%M:%S',
'%Y-%m-%d %H:%M:%S.%f',
diff --git a/youtube_dl/version.py b/youtube_dl/version.py
index b48552031..f7ad846d9 100644
--- a/youtube_dl/version.py
+++ b/youtube_dl/version.py
@@ -1,3 +1,3 @@
from __future__ import unicode_literals
-__version__ = '2016.08.07'
+__version__ = '2016.08.10'
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-16 14:33:58 +0000