From c41a2ec4af9fa76b04b6d9f50d9a895d124ea14c Mon Sep 17 00:00:00 2001 From: tiktok Date: Mon, 23 Mar 2015 01:42:17 +0100 Subject: [MiomioTv] Add new extractor --- docs/supportedsites.md | 1 + youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/miomio_tv.py | 70 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 72 insertions(+) create mode 100644 youtube_dl/extractor/miomio_tv.py diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 062cb3d62..53d280677 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -244,6 +244,7 @@ - **Mgoon** - **Minhateca** - **MinistryGrid** + - **Miomio.tv** - **mitele.es** - **mixcloud** - **MLB** diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index ffcc7d9ab..370154773 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -265,6 +265,7 @@ from .mdr import MDRIE from .metacafe import MetacafeIE from .metacritic import MetacriticIE from .mgoon import MgoonIE +from .miomio_tv import MiomioTvIE from .minhateca import MinhatecaIE from .ministrygrid import MinistryGridIE from .mit import TechTVMITIE, MITIE, OCWMITIE diff --git a/youtube_dl/extractor/miomio_tv.py b/youtube_dl/extractor/miomio_tv.py new file mode 100644 index 000000000..355774f54 --- /dev/null +++ b/youtube_dl/extractor/miomio_tv.py @@ -0,0 +1,70 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class MiomioTvIE(InfoExtractor): + IE_NAME = 'miomio.tv' + _VALID_URL = r'https?://(?:www\.)?miomio\.tv/watch/cc(?P[0-9]+)' + _TEST = { + 'url': 'http://www.miomio.tv/watch/cc179734/', + 'md5': '48de02137d0739c15b440a224ad364b9', + 'info_dict': { + 'id': '179734', + 'title': u'\u624b\u7ed8\u52a8\u6f2b\u9b3c\u6ce3\u4f46\u4e01\u5168\u7a0b\u753b\u6cd5', + 'ext': 'flv' + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex(r' Date: Mon, 23 Mar 2015 23:16:50 +0100 Subject: [MiomioTv] updated based on feedback to merge request: 1) added comment to explain extra xml link download 2) changed {} entries to {0}, {1} etc 3) removed redundant language header (the others are required) 4) checked out the old version of the supported sites md (the change was not required) --- docs/supportedsites.md | 1 - youtube_dl/extractor/miomio_tv.py | 12 ++++++++---- 2 files changed, 8 insertions(+), 5 deletions(-) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 53d280677..062cb3d62 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -244,7 +244,6 @@ - **Mgoon** - **Minhateca** - **MinistryGrid** - - **Miomio.tv** - **mitele.es** - **mixcloud** - **MLB** diff --git a/youtube_dl/extractor/miomio_tv.py b/youtube_dl/extractor/miomio_tv.py index 355774f54..ae20a32fa 100644 --- a/youtube_dl/extractor/miomio_tv.py +++ b/youtube_dl/extractor/miomio_tv.py @@ -23,10 +23,15 @@ class MiomioTvIE(InfoExtractor): title = self._html_search_regex(r' Date: Thu, 2 Apr 2015 22:32:16 +0600 Subject: [miomio] Simplify and fix python 2.6 issue --- youtube_dl/extractor/miomio_tv.py | 93 +++++++++++++++++++++++---------------- 1 file changed, 56 insertions(+), 37 deletions(-) diff --git a/youtube_dl/extractor/miomio_tv.py b/youtube_dl/extractor/miomio_tv.py index ae20a32fa..dc2ba7cb4 100644 --- a/youtube_dl/extractor/miomio_tv.py +++ b/youtube_dl/extractor/miomio_tv.py @@ -1,74 +1,93 @@ # coding: utf-8 from __future__ import unicode_literals +import random + from .common import InfoExtractor +from ..utils import ( + xpath_text, + int_or_none, +) class MiomioTvIE(InfoExtractor): IE_NAME = 'miomio.tv' _VALID_URL = r'https?://(?:www\.)?miomio\.tv/watch/cc(?P[0-9]+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.miomio.tv/watch/cc179734/', 'md5': '48de02137d0739c15b440a224ad364b9', 'info_dict': { 'id': '179734', - 'title': u'\u624b\u7ed8\u52a8\u6f2b\u9b3c\u6ce3\u4f46\u4e01\u5168\u7a0b\u753b\u6cd5', - 'ext': 'flv' - } - } + 'ext': 'flv', + 'title': '手绘动漫鬼泣但丁全程画法', + 'duration': 354, + }, + }, { + 'url': 'http://www.miomio.tv/watch/cc184024/', + 'info_dict': { + 'id': '43729', + 'title': '《动漫同人插画绘制》', + }, + 'playlist_mincount': 86, + }] def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - title = self._html_search_regex(r' Date: Thu, 2 Apr 2015 22:33:30 +0600 Subject: [miomio] Rename extractor --- youtube_dl/extractor/__init__.py | 2 +- youtube_dl/extractor/miomio.py | 93 +++++++++++++++++++++++++++++++++++++++ youtube_dl/extractor/miomio_tv.py | 93 --------------------------------------- 3 files changed, 94 insertions(+), 94 deletions(-) create mode 100644 youtube_dl/extractor/miomio.py delete mode 100644 youtube_dl/extractor/miomio_tv.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 0b9736f2d..9700d81f5 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -274,7 +274,7 @@ from .mdr import MDRIE from .metacafe import MetacafeIE from .metacritic import MetacriticIE from .mgoon import MgoonIE -from .miomio_tv import MiomioTvIE +from .miomio import MioMioIE from .minhateca import MinhatecaIE from .ministrygrid import MinistryGridIE from .mit import TechTVMITIE, MITIE, OCWMITIE diff --git a/youtube_dl/extractor/miomio.py b/youtube_dl/extractor/miomio.py new file mode 100644 index 000000000..11608f730 --- /dev/null +++ b/youtube_dl/extractor/miomio.py @@ -0,0 +1,93 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import random + +from .common import InfoExtractor +from ..utils import ( + xpath_text, + int_or_none, +) + + +class MioMioIE(InfoExtractor): + IE_NAME = 'miomio.tv' + _VALID_URL = r'https?://(?:www\.)?miomio\.tv/watch/cc(?P[0-9]+)' + _TESTS = [{ + 'url': 'http://www.miomio.tv/watch/cc179734/', + 'md5': '48de02137d0739c15b440a224ad364b9', + 'info_dict': { + 'id': '179734', + 'ext': 'flv', + 'title': '手绘动漫鬼泣但丁全程画法', + 'duration': 354, + }, + }, { + 'url': 'http://www.miomio.tv/watch/cc184024/', + 'info_dict': { + 'id': '43729', + 'title': '《动漫同人插画绘制》', + }, + 'playlist_mincount': 86, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + title = self._html_search_meta( + 'description', webpage, 'title', fatal=True) + + mioplayer_path = self._search_regex( + r'src="(/mioplayer/[^"]+)"', webpage, 'ref_path') + + xml_config = self._search_regex( + r'flashvars="type=sina&(.+?)&', + webpage, 'xml config') + + # skipping the following page causes lags and eventually connection drop-outs + self._request_webpage( + 'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/xml.php?id=%s&r=%s' % (id, random.randint(100, 999)), + video_id) + + # the following xml contains the actual configuration information on the video file(s) + vid_config = self._download_xml( + 'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/sina.php?{0}'.format(xml_config), + video_id) + + http_headers = { + 'Referer': 'http://www.miomio.tv%s' % mioplayer_path, + } + + entries = [] + for f in vid_config.findall('./durl'): + segment_url = xpath_text(f, 'url', 'video url') + if not segment_url: + continue + order = xpath_text(f, 'order', 'order') + segment_id = video_id + segment_title = title + if order: + segment_id += '-%s' % order + segment_title += ' part %s' % order + entries.append({ + 'id': segment_id, + 'url': segment_url, + 'title': segment_title, + 'duration': int_or_none(xpath_text(f, 'length', 'duration'), 1000), + 'http_headers': http_headers, + }) + + if len(entries) == 1: + segment = entries[0] + segment['id'] = video_id + segment['title'] = title + return segment + + return { + '_type': 'multi_video', + 'id': video_id, + 'entries': entries, + 'title': title, + 'http_headers': http_headers, + } diff --git a/youtube_dl/extractor/miomio_tv.py b/youtube_dl/extractor/miomio_tv.py deleted file mode 100644 index dc2ba7cb4..000000000 --- a/youtube_dl/extractor/miomio_tv.py +++ /dev/null @@ -1,93 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import random - -from .common import InfoExtractor -from ..utils import ( - xpath_text, - int_or_none, -) - - -class MiomioTvIE(InfoExtractor): - IE_NAME = 'miomio.tv' - _VALID_URL = r'https?://(?:www\.)?miomio\.tv/watch/cc(?P[0-9]+)' - _TESTS = [{ - 'url': 'http://www.miomio.tv/watch/cc179734/', - 'md5': '48de02137d0739c15b440a224ad364b9', - 'info_dict': { - 'id': '179734', - 'ext': 'flv', - 'title': '手绘动漫鬼泣但丁全程画法', - 'duration': 354, - }, - }, { - 'url': 'http://www.miomio.tv/watch/cc184024/', - 'info_dict': { - 'id': '43729', - 'title': '《动漫同人插画绘制》', - }, - 'playlist_mincount': 86, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - title = self._html_search_meta( - 'description', webpage, 'title', fatal=True) - - mioplayer_path = self._search_regex( - r'src="(/mioplayer/[^"]+)"', webpage, 'ref_path') - - xml_config = self._search_regex( - r'flashvars="type=sina&(.+?)&', - webpage, 'xml config') - - # skipping the following page causes lags and eventually connection drop-outs - self._request_webpage( - 'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/xml.php?id=%s&r=%s' % (id, random.randint(100, 999)), - video_id) - - # the following xml contains the actual configuration information on the video file(s) - vid_config = self._download_xml( - 'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/sina.php?{0}'.format(xml_config), - video_id) - - http_headers = { - 'Referer': 'http://www.miomio.tv%s' % mioplayer_path, - } - - entries = [] - for f in vid_config.findall('./durl'): - segment_url = xpath_text(f, 'url', 'video url') - if not segment_url: - continue - order = xpath_text(f, 'order', 'order') - segment_id = video_id - segment_title = title - if order: - segment_id += '-%s' % order - segment_title += ' part %s' % order - entries.append({ - 'id': segment_id, - 'url': segment_url, - 'title': segment_title, - 'duration': int_or_none(xpath_text(f, 'length', 'duration'), 1000), - 'http_headers': http_headers, - }) - - if len(entries) == 1: - segment = entries[0] - segment['id'] = video_id - segment['title'] = title - return segment - - return { - '_type': 'multi_video', - 'id': video_id, - 'entries': entries, - 'title': title, - 'http_headers': http_headers, - } -- cgit v1.2.3 From 2ec8e04cac895121a71f11a44b855b1bf8a0195e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 2 Apr 2015 22:34:08 +0600 Subject: [miomio] Fix alphabetic order --- youtube_dl/extractor/__init__.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 9700d81f5..aae4aae4c 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -274,9 +274,9 @@ from .mdr import MDRIE from .metacafe import MetacafeIE from .metacritic import MetacriticIE from .mgoon import MgoonIE -from .miomio import MioMioIE from .minhateca import MinhatecaIE from .ministrygrid import MinistryGridIE +from .miomio import MioMioIE from .mit import TechTVMITIE, MITIE, OCWMITIE from .mitele import MiTeleIE from .mixcloud import MixcloudIE -- cgit v1.2.3