From bfe96d7bea7c5227456bf1aecca51907c8f30c51 Mon Sep 17 00:00:00 2001 From: Philip Huppert Date: Fri, 9 Oct 2015 18:38:11 +0200 Subject: [PATCH 1/4] [presstv] Added extractor PressTV. Fixes #7060 --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/presstv.py | 80 ++++++++++++++++++++++++++++++ 2 files changed, 81 insertions(+) create mode 100644 youtube_dl/extractor/presstv.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index de29c7956..c2fa83918 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -583,6 +583,7 @@ from .pornotube import PornotubeIE from .pornovoisines import PornoVoisinesIE from .pornoxo import PornoXOIE +from .presstv import PressTVIE from .primesharetv import PrimeShareTVIE from .promptfile import PromptFileIE from .prosiebensat1 import ProSiebenSat1IE diff --git a/youtube_dl/extractor/presstv.py b/youtube_dl/extractor/presstv.py new file mode 100644 index 000000000..724d8b1c4 --- /dev/null +++ b/youtube_dl/extractor/presstv.py @@ -0,0 +1,80 @@ +# coding: utf-8 +from __future__ import unicode_literals +import re + +from .common import InfoExtractor +from ..utils import str_to_int + + +class PressTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?presstv\.ir/Video/(?P[0-9]+)/(?P[0-9]+)/(?P[0-9]+)/(?P[0-9]+)/' + + _TEST = { + 'url': 'http://www.presstv.ir/Video/2015/10/04/431915/Max-Igan-Press-TV-Face-to-Face', + 'md5': 'e95736ac75088b5f1e5bbb68f248f90d', + 'info_dict': { + 'id': '431915', + 'ext': 'mp4', + 'title': 'Press TV’s full interview with Max Igan', + 'upload_date': '20151004', + 'thumbnail': 'http://217.218.67.233/photo/20151004/d5c333ad-98f9-4bd3-bc3e-a1ad6a192803.jpg', + 'description': ('Watch Press TV’s full interview with Max Igan, a radio talk show host and political ' + 'commentator.\nThe interview, conducted on Press TV’s Face ' + 'to Face program, was aired on October 3, 2015.') + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + # extract video URL from webpage + video_url = self._html_search_regex(r'', webpage, + 'Video URL') + + # build list of available formats + # specified in http://www.presstv.ir/Scripts/playback.js + base_url = 'http://192.99.219.222:82/presstv' + formats = [ + { + 'url': base_url + video_url, + 'format': '1080p mp4', + 'format_id': '1080p' + }, { + 'url': base_url + video_url.replace(".mp4", "_low800.mp4"), + 'format': '720p mp4', + 'format_id': '720p' + }, { + 'url': base_url + video_url.replace(".mp4", "_low400.mp4"), + 'format': '360p mp4', + 'format_id': '360p' + }, { + 'url': base_url + video_url.replace(".mp4", "_low200.mp4"), + 'format': '180p mp4', + 'format_id': '180p' + } + ] + formats.reverse() + + # extract video metadata + title = self._html_search_meta('title', webpage, 'Title', True) + title = title.partition(' - ')[2] + + description = self._html_search_regex(r'
(.*?)
', webpage, + 'Description', flags=re.DOTALL) + + thumbnail = self._html_search_meta('og:image', webpage, 'Thumbnail', True) + + year = str_to_int(self._search_regex(PressTVIE._VALID_URL, url, 'Upload year', group='y')) + month = str_to_int(self._search_regex(PressTVIE._VALID_URL, url, 'Upload month', group='m')) + day = str_to_int(self._search_regex(PressTVIE._VALID_URL, url, 'Upload day', group='d')) + upload_date = '%04d%02d%02d' % (year, month, day) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + 'upload_date': upload_date, + 'description': description + } From 95153a960d098d75e6100e38e77fdaa32f5267a2 Mon Sep 17 00:00:00 2001 From: Philip Huppert Date: Sat, 9 Apr 2016 16:14:05 +0200 Subject: [PATCH 2/4] [presstv] updated extractor and tests to work with current PressTV website --- youtube_dl/extractor/presstv.py | 26 ++++++++++++-------------- 1 file changed, 12 insertions(+), 14 deletions(-) diff --git a/youtube_dl/extractor/presstv.py b/youtube_dl/extractor/presstv.py index 724d8b1c4..9af6780c1 100644 --- a/youtube_dl/extractor/presstv.py +++ b/youtube_dl/extractor/presstv.py @@ -7,20 +7,20 @@ class PressTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?presstv\.ir/Video/(?P[0-9]+)/(?P[0-9]+)/(?P[0-9]+)/(?P[0-9]+)/' + _VALID_URL = r'https?://(?:www\.)?presstv\.ir/[^/]+/(?P[0-9]+)/(?P[0-9]+)/(?P[0-9]+)/(?P[0-9]+)/' _TEST = { - 'url': 'http://www.presstv.ir/Video/2015/10/04/431915/Max-Igan-Press-TV-Face-to-Face', - 'md5': 'e95736ac75088b5f1e5bbb68f248f90d', + 'url': 'http://www.presstv.ir/Detail/2016/04/09/459911/Australian-sewerage-treatment-facility-/', + 'md5': '5d7e3195a447cb13e9267e931d8dd5a5', 'info_dict': { - 'id': '431915', + 'id': '459911', 'ext': 'mp4', - 'title': 'Press TV’s full interview with Max Igan', - 'upload_date': '20151004', - 'thumbnail': 'http://217.218.67.233/photo/20151004/d5c333ad-98f9-4bd3-bc3e-a1ad6a192803.jpg', - 'description': ('Watch Press TV’s full interview with Max Igan, a radio talk show host and political ' - 'commentator.\nThe interview, conducted on Press TV’s Face ' - 'to Face program, was aired on October 3, 2015.') + 'title': 'Organic mattresses used to clean waste water', + 'upload_date': '20160409', + 'thumbnail': 'http://media.presstv.com/photo/20160409/41719129-76fa-4372-a09d-bf348278eb5d.jpg', + 'description': ('A trial program at an Australian sewerage treatment facility hopes to change ' + 'the way waste water is treated by using plant mattresses to reduce chemical ' + 'and electricity use.') } } @@ -58,12 +58,10 @@ def _real_extract(self, url): # extract video metadata title = self._html_search_meta('title', webpage, 'Title', True) - title = title.partition(' - ')[2] - - description = self._html_search_regex(r'
(.*?)
', webpage, - 'Description', flags=re.DOTALL) + title = title.partition('-')[2].strip() thumbnail = self._html_search_meta('og:image', webpage, 'Thumbnail', True) + description = self._html_search_meta('og:description', webpage, 'Description', True) year = str_to_int(self._search_regex(PressTVIE._VALID_URL, url, 'Upload year', group='y')) month = str_to_int(self._search_regex(PressTVIE._VALID_URL, url, 'Upload month', group='m')) From de728757ad7218ce175649ec0d3f0b5723f2c580 Mon Sep 17 00:00:00 2001 From: Philip Huppert Date: Sun, 10 Apr 2016 16:36:44 +0200 Subject: [PATCH 3/4] [presstv] Refactored extractor. --- youtube_dl/extractor/presstv.py | 52 +++++++++++++++------------------ 1 file changed, 23 insertions(+), 29 deletions(-) diff --git a/youtube_dl/extractor/presstv.py b/youtube_dl/extractor/presstv.py index 9af6780c1..755e32528 100644 --- a/youtube_dl/extractor/presstv.py +++ b/youtube_dl/extractor/presstv.py @@ -17,10 +17,8 @@ class PressTVIE(InfoExtractor): 'ext': 'mp4', 'title': 'Organic mattresses used to clean waste water', 'upload_date': '20160409', - 'thumbnail': 'http://media.presstv.com/photo/20160409/41719129-76fa-4372-a09d-bf348278eb5d.jpg', - 'description': ('A trial program at an Australian sewerage treatment facility hopes to change ' - 'the way waste water is treated by using plant mattresses to reduce chemical ' - 'and electricity use.') + 'thumbnail': 're:^https?://.*\.jpg', + 'description': 'md5:20002e654bbafb6908395a5c0cfcd125' } } @@ -35,38 +33,34 @@ def _real_extract(self, url): # build list of available formats # specified in http://www.presstv.ir/Scripts/playback.js base_url = 'http://192.99.219.222:82/presstv' - formats = [ - { - 'url': base_url + video_url, - 'format': '1080p mp4', - 'format_id': '1080p' - }, { - 'url': base_url + video_url.replace(".mp4", "_low800.mp4"), - 'format': '720p mp4', - 'format_id': '720p' - }, { - 'url': base_url + video_url.replace(".mp4", "_low400.mp4"), - 'format': '360p mp4', - 'format_id': '360p' - }, { - 'url': base_url + video_url.replace(".mp4", "_low200.mp4"), - 'format': '180p mp4', - 'format_id': '180p' - } + _formats = [ + ("180p", "_low200.mp4"), + ("360p", "_low400.mp4"), + ("720p", "_low800.mp4"), + ("1080p", ".mp4") ] - formats.reverse() + + formats = [] + for fmt in _formats: + format_id, extension = fmt + formats.append({ + 'url': base_url + video_url[:-4] + extension, + 'format_id': format_id + }) # extract video metadata title = self._html_search_meta('title', webpage, 'Title', True) title = title.partition('-')[2].strip() - thumbnail = self._html_search_meta('og:image', webpage, 'Thumbnail', True) - description = self._html_search_meta('og:description', webpage, 'Description', True) + thumbnail = self._og_search_thumbnail(webpage) + description = self._og_search_description(webpage) - year = str_to_int(self._search_regex(PressTVIE._VALID_URL, url, 'Upload year', group='y')) - month = str_to_int(self._search_regex(PressTVIE._VALID_URL, url, 'Upload month', group='m')) - day = str_to_int(self._search_regex(PressTVIE._VALID_URL, url, 'Upload day', group='d')) - upload_date = '%04d%02d%02d' % (year, month, day) + match = re.match(PressTVIE._VALID_URL, url) + upload_date = '%04d%02d%02d' % ( + str_to_int(match.group('y')), + str_to_int(match.group('m')), + str_to_int(match.group('d')) + ) return { 'id': video_id, From dfbc7f7f3f44ff7f9ed2beff76dc37edbb66af8d Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Mon, 11 Apr 2016 16:14:07 +0800 Subject: [PATCH 4/4] [presstv] Improve and simplify --- youtube_dl/extractor/presstv.py | 48 +++++++++++++++++---------------- 1 file changed, 25 insertions(+), 23 deletions(-) diff --git a/youtube_dl/extractor/presstv.py b/youtube_dl/extractor/presstv.py index 755e32528..2da93ed34 100644 --- a/youtube_dl/extractor/presstv.py +++ b/youtube_dl/extractor/presstv.py @@ -1,19 +1,21 @@ # coding: utf-8 from __future__ import unicode_literals + import re from .common import InfoExtractor -from ..utils import str_to_int +from ..utils import remove_start class PressTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?presstv\.ir/[^/]+/(?P[0-9]+)/(?P[0-9]+)/(?P[0-9]+)/(?P[0-9]+)/' + _VALID_URL = r'https?://(?:www\.)?presstv\.ir/[^/]+/(?P\d+)/(?P\d+)/(?P\d+)/(?P\d+)/(?P[^/]+)?' _TEST = { 'url': 'http://www.presstv.ir/Detail/2016/04/09/459911/Australian-sewerage-treatment-facility-/', 'md5': '5d7e3195a447cb13e9267e931d8dd5a5', 'info_dict': { 'id': '459911', + 'display_id': 'Australian-sewerage-treatment-facility-', 'ext': 'mp4', 'title': 'Organic mattresses used to clean waste water', 'upload_date': '20160409', @@ -23,47 +25,47 @@ class PressTVIE(InfoExtractor): } def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') or video_id + + webpage = self._download_webpage(url, display_id) # extract video URL from webpage - video_url = self._html_search_regex(r'', webpage, - 'Video URL') + video_url = self._hidden_inputs(webpage)['inpPlayback'] # build list of available formats # specified in http://www.presstv.ir/Scripts/playback.js base_url = 'http://192.99.219.222:82/presstv' _formats = [ - ("180p", "_low200.mp4"), - ("360p", "_low400.mp4"), - ("720p", "_low800.mp4"), - ("1080p", ".mp4") + (180, '_low200.mp4'), + (360, '_low400.mp4'), + (720, '_low800.mp4'), + (1080, '.mp4') ] - formats = [] - for fmt in _formats: - format_id, extension = fmt - formats.append({ - 'url': base_url + video_url[:-4] + extension, - 'format_id': format_id - }) + formats = [{ + 'url': base_url + video_url[:-4] + extension, + 'format_id': '%dp' % height, + 'height': height, + } for height, extension in _formats] # extract video metadata - title = self._html_search_meta('title', webpage, 'Title', True) - title = title.partition('-')[2].strip() + title = remove_start( + self._html_search_meta('title', webpage, fatal=True), 'PressTV-') thumbnail = self._og_search_thumbnail(webpage) description = self._og_search_description(webpage) - match = re.match(PressTVIE._VALID_URL, url) upload_date = '%04d%02d%02d' % ( - str_to_int(match.group('y')), - str_to_int(match.group('m')), - str_to_int(match.group('d')) + int(mobj.group('y')), + int(mobj.group('m')), + int(mobj.group('d')), ) return { 'id': video_id, + 'display_id': display_id, 'title': title, 'formats': formats, 'thumbnail': thumbnail,