diff options
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 2 | ||||
-rw-r--r-- | youtube_dl/extractor/ctsnews.py | 94 | ||||
-rw-r--r-- | youtube_dl/extractor/srmediathek.py | 2 | ||||
-rw-r--r-- | youtube_dl/extractor/viddler.py | 2 | ||||
-rw-r--r-- | youtube_dl/extractor/xuite.py | 142 |
5 files changed, 240 insertions, 2 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 444af8b6e..ad4ed103b 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -82,6 +82,7 @@ from .crunchyroll import ( CrunchyrollShowPlaylistIE ) from .cspan import CSpanIE +from .ctsnews import CtsNewsIE from .dailymotion import ( DailymotionIE, DailymotionPlaylistIE, @@ -552,6 +553,7 @@ from .xminus import XMinusIE from .xnxx import XNXXIE from .xvideos import XVideosIE from .xtube import XTubeUserIE, XTubeIE +from .xuite import XuiteIE from .xxxymovies import XXXYMoviesIE from .yahoo import ( YahooIE, diff --git a/youtube_dl/extractor/ctsnews.py b/youtube_dl/extractor/ctsnews.py new file mode 100644 index 000000000..f769dc031 --- /dev/null +++ b/youtube_dl/extractor/ctsnews.py @@ -0,0 +1,94 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_urllib_request +from ..utils import parse_iso8601, ExtractorError + + +class CtsNewsIE(InfoExtractor): + # https connection failed (Connection reset) + _VALID_URL = r'http://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', + 'md5': 'a9875cb790252b08431186d741beaabe', + 'info_dict': { + 'id': '201501291578109', + 'ext': 'mp4', + 'title': '以色列.真主黨交火 3人死亡', + 'description': 'md5:95e9b295c898b7ff294f09d450178d7d', + 'timestamp': 1422528540, + 'upload_date': '20150129', + } + }, { + # News count not appear on page but still available in database + 'url': 'http://news.cts.com.tw/cts/international/201309/201309031304098.html', + 'md5': '3aee7e0df7cdff94e43581f54c22619e', + 'info_dict': { + 'id': '201309031304098', + 'ext': 'mp4', + 'title': '韓國31歲童顏男 貌如十多歲小孩', + 'description': 'md5:f183feeba3752b683827aab71adad584', + 'thumbnail': 're:^https?://.*\.jpg$', + 'timestamp': 1378205880, + 'upload_date': '20130903', + } + }, { + # With Youtube embedded video + 'url': 'http://news.cts.com.tw/cts/money/201501/201501291578003.html', + 'md5': '1d842c771dc94c8c3bca5af2cc1db9c5', + 'add_ie': ['Youtube'], + 'info_dict': { + 'id': 'OVbfO7d0_hQ', + 'ext': 'mp4', + 'title': 'iPhone6熱銷 蘋果財報亮眼', + 'description': 'md5:f395d4f485487bb0f992ed2c4b07aa7d', + 'thumbnail': 're:^https?://.*\.jpg$', + 'upload_date': '20150128', + 'uploader_id': 'TBSCTS', + 'uploader': '中華電視公司', + } + }] + + 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') + 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) + + return { + '_type': 'url', + 'url': youtube_url, + 'ie_key': 'Youtube', + } + + description = self._html_search_meta('description', page) + title = self._html_search_meta('title', page) + 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=' ') + + return { + 'id': news_id, + 'url': video_url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + } diff --git a/youtube_dl/extractor/srmediathek.py b/youtube_dl/extractor/srmediathek.py index 666a7dcc8..5d583c720 100644 --- a/youtube_dl/extractor/srmediathek.py +++ b/youtube_dl/extractor/srmediathek.py @@ -8,7 +8,7 @@ from ..utils import js_to_json class SRMediathekIE(InfoExtractor): - IE_DESC = 'Süddeutscher Rundfunk' + IE_DESC = 'Saarländischer Rundfunk' _VALID_URL = r'https?://sr-mediathek\.sr-online\.de/index\.php\?.*?&id=(?P<id>[0-9]+)' _TEST = { diff --git a/youtube_dl/extractor/viddler.py b/youtube_dl/extractor/viddler.py index ef104dc29..8516a2940 100644 --- a/youtube_dl/extractor/viddler.py +++ b/youtube_dl/extractor/viddler.py @@ -6,7 +6,7 @@ from ..utils import ( int_or_none, ) from ..compat import ( - compat_urllib_request + compat_urllib_request ) diff --git a/youtube_dl/extractor/xuite.py b/youtube_dl/extractor/xuite.py new file mode 100644 index 000000000..4971965f9 --- /dev/null +++ b/youtube_dl/extractor/xuite.py @@ -0,0 +1,142 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +import base64 + +from .common import InfoExtractor +from ..compat import compat_urllib_parse_unquote +from ..utils import ( + ExtractorError, + parse_iso8601, + parse_duration, +) + + +class XuiteIE(InfoExtractor): + _REGEX_BASE64 = r'(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{2}==|[A-Za-z0-9+/]{3}=)?' + _VALID_URL = r'https?://vlog\.xuite\.net/(?:play|embed)/(?P<id>%s)' % _REGEX_BASE64 + _TESTS = [{ + # Audio + 'url': 'http://vlog.xuite.net/play/RGkzc1ZULTM4NjA5MTQuZmx2', + 'md5': '63a42c705772aa53fd4c1a0027f86adf', + 'info_dict': { + 'id': '3860914', + 'ext': 'mp3', + 'title': '孤單南半球-歐德陽', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 247.246, + 'timestamp': 1314932940, + 'upload_date': '20110902', + 'uploader': '阿能', + 'uploader_id': '15973816', + 'categories': ['個人短片'], + }, + }, { + # Video with only one format + 'url': 'http://vlog.xuite.net/play/TkRZNjhULTM0NDE2MjkuZmx2', + 'md5': 'c45737fc8ac5dc8ac2f92ecbcecf505e', + 'info_dict': { + 'id': '3441629', + 'ext': 'mp4', + 'title': '孫燕姿 - 眼淚成詩', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 217.399, + 'timestamp': 1299383640, + 'upload_date': '20110306', + 'uploader': 'Valen', + 'uploader_id': '10400126', + 'categories': ['影視娛樂'], + }, + }, { + # Video with two formats + 'url': 'http://vlog.xuite.net/play/bWo1N1pLLTIxMzAxMTcwLmZsdg==', + 'md5': '1166e0f461efe55b62e26a2d2a68e6de', + 'info_dict': { + 'id': '21301170', + 'ext': 'mp4', + 'title': '暗殺教室 02', + 'description': '字幕:【極影字幕社】', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 1384.907, + 'timestamp': 1421481240, + 'upload_date': '20150117', + 'uploader': '我只是想認真點', + 'uploader_id': '242127761', + 'categories': ['電玩動漫'], + }, + }, { + 'url': 'http://vlog.xuite.net/play/S1dDUjdyLTMyOTc3NjcuZmx2/%E5%AD%AB%E7%87%95%E5%A7%BF-%E7%9C%BC%E6%B7%9A%E6%88%90%E8%A9%A9', + 'only_matching': True, + }] + + def _extract_flv_config(self, media_id): + base64_media_id = base64.b64encode(media_id.encode('utf-8')).decode('utf-8') + flv_config = self._download_xml( + 'http://vlog.xuite.net/flash/player?media=%s' % base64_media_id, + 'flv config') + prop_dict = {} + for prop in flv_config.findall('./property'): + prop_id = base64.b64decode(prop.attrib['id']).decode('utf-8') + # CDATA may be empty in flv config + if not prop.text: + continue + encoded_content = base64.b64decode(prop.text).decode('utf-8') + prop_dict[prop_id] = compat_urllib_parse_unquote(encoded_content) + return prop_dict + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + error_msg = self._search_regex( + r'<div id="error-message-content">([^<]+)', + webpage, 'error message', default=None) + if error_msg: + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, error_msg), + expected=True) + + video_id = self._html_search_regex( + r'data-mediaid="(\d+)"', webpage, 'media id') + flv_config = self._extract_flv_config(video_id) + + FORMATS = { + 'audio': 'mp3', + 'video': 'mp4', + } + + formats = [] + for format_tag in ('src', 'hq_src'): + video_url = flv_config.get(format_tag) + if not video_url: + continue + format_id = self._search_regex( + r'\bq=(.+?)\b', video_url, 'format id', default=format_tag) + formats.append({ + 'url': video_url, + 'ext': FORMATS.get(flv_config['type'], 'mp4'), + 'format_id': format_id, + 'height': int(format_id) if format_id.isnumeric() else None, + }) + self._sort_formats(formats) + + timestamp = flv_config.get('publish_datetime') + if timestamp: + timestamp = parse_iso8601(timestamp + ' +0800', ' ') + + category = flv_config.get('category') + categories = [category] if category else [] + + return { + 'id': video_id, + 'title': flv_config['title'], + 'description': flv_config.get('description'), + 'thumbnail': flv_config.get('thumb'), + 'timestamp': timestamp, + 'uploader': flv_config.get('author_name'), + 'uploader_id': flv_config.get('author_id'), + 'duration': parse_duration(flv_config.get('duration')), + 'categories': categories, + 'formats': formats, + } |