From 6a1c4fbfcb57c138b8ace305127c2654844e8099 Mon Sep 17 00:00:00 2001 From: peugeot Date: Fri, 26 Dec 2014 15:49:12 +0100 Subject: [PATCH 1/3] [hellporno] new extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/hellporno.py | 56 +++++++++++++++++++++++++++++++ 2 files changed, 57 insertions(+) create mode 100644 youtube_dl/extractor/hellporno.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index fd0ebffe3..de5206729 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -166,6 +166,7 @@ from .grooveshark import GroovesharkIE from .groupon import GrouponIE from .hark import HarkIE from .heise import HeiseIE +from .hellporno import HellPornoIE from .helsinki import HelsinkiIE from .hentaistigma import HentaiStigmaIE from .hornbunny import HornBunnyIE diff --git a/youtube_dl/extractor/hellporno.py b/youtube_dl/extractor/hellporno.py new file mode 100644 index 000000000..06f85127f --- /dev/null +++ b/youtube_dl/extractor/hellporno.py @@ -0,0 +1,56 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + +class HellPornoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?hellporno\.com/videos/(?P[^/]+)' + _TEST = { + 'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/', + 'md5': '1fee339c610d2049699ef2aa699439f1', + 'info_dict': { + 'id': '149116', + 'ext': 'mp4', + 'title': 'Dixie is posing with naked ass very erotic', + 'description': 'md5:5ba02cbf31eff820147b3cc25306d89a', + 'categories': list, # NSFW + 'thumbnail': 're:https?://.*\.jpg$', + 'age_limit': 18, + } + } + + def _real_extract(self, url): + webpage = self._download_webpage(url, 'main') + + video_id = self._html_search_regex(r'video_id:\s*\'([^\']+)\'', webpage, 'id') + + video_url = self._html_search_regex(r'video_url:\s*\'([^\']+)\'', webpage, 'video_url') + + ext = self._html_search_regex(r'postfix:\s*\'([^\']+)\'', webpage, 'ext')[1:] + + title = self._html_search_regex( + r'([^<]+)\s*-\s*Hell Porno', webpage, 'title') + + description = self._html_search_meta('description', webpage, 'description', fatal=False) + + thumbnail = self._html_search_regex( + r'preview_url:\s*\'([^\']+)\'', + webpage, 'thumbnail', fatal=False) + + categories_str = self._html_search_regex( + r' Date: Mon, 29 Dec 2014 10:38:07 +0100 Subject: [PATCH 2/3] [hellporno] simplify --- youtube_dl/extractor/hellporno.py | 32 ++++++++++++++----------------- 1 file changed, 14 insertions(+), 18 deletions(-) diff --git a/youtube_dl/extractor/hellporno.py b/youtube_dl/extractor/hellporno.py index 06f85127f..754322cdf 100644 --- a/youtube_dl/extractor/hellporno.py +++ b/youtube_dl/extractor/hellporno.py @@ -1,55 +1,51 @@ from __future__ import unicode_literals - -import re - from .common import InfoExtractor + class HellPornoIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?hellporno\.com/videos/(?P[^/]+)' + _VALID_URL = r'https?://(?:www\.)?hellporno\.com/videos/(?P[^/]+)' _TEST = { 'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/', 'md5': '1fee339c610d2049699ef2aa699439f1', 'info_dict': { 'id': '149116', + 'display_id': 'dixie-is-posing-with-naked-ass-very-erotic', 'ext': 'mp4', 'title': 'Dixie is posing with naked ass very erotic', - 'description': 'md5:5ba02cbf31eff820147b3cc25306d89a', - 'categories': list, # NSFW 'thumbnail': 're:https?://.*\.jpg$', 'age_limit': 18, } } def _real_extract(self, url): - webpage = self._download_webpage(url, 'main') + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) - video_id = self._html_search_regex(r'video_id:\s*\'([^\']+)\'', webpage, 'id') + video_id = self._html_search_regex( + r'video_id:\s*\'([^\']+)\'', webpage, 'id') - video_url = self._html_search_regex(r'video_url:\s*\'([^\']+)\'', webpage, 'video_url') + ext = self._html_search_regex( + r'postfix:\s*\'([^\']+)\'', webpage, 'ext')[1:] - ext = self._html_search_regex(r'postfix:\s*\'([^\']+)\'', webpage, 'ext')[1:] + video_url = self._html_search_regex( + r'video_url:\s*\'([^\']+)\'', webpage, 'video_url') title = self._html_search_regex( r'([^<]+)\s*-\s*Hell Porno', webpage, 'title') - description = self._html_search_meta('description', webpage, 'description', fatal=False) - thumbnail = self._html_search_regex( r'preview_url:\s*\'([^\']+)\'', webpage, 'thumbnail', fatal=False) - categories_str = self._html_search_regex( - r' Date: Mon, 29 Dec 2014 21:33:41 +0600 Subject: [PATCH 3/3] [hellporno] Extract all formats and improve --- youtube_dl/extractor/hellporno.py | 47 ++++++++++++++++++++++--------- 1 file changed, 33 insertions(+), 14 deletions(-) diff --git a/youtube_dl/extractor/hellporno.py b/youtube_dl/extractor/hellporno.py index 754322cdf..7a1c75b65 100644 --- a/youtube_dl/extractor/hellporno.py +++ b/youtube_dl/extractor/hellporno.py @@ -1,5 +1,12 @@ from __future__ import unicode_literals + +import re + from .common import InfoExtractor +from ..utils import ( + js_to_json, + remove_end, +) class HellPornoIE(InfoExtractor): @@ -19,23 +26,36 @@ class HellPornoIE(InfoExtractor): def _real_extract(self, url): display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) - video_id = self._html_search_regex( - r'video_id:\s*\'([^\']+)\'', webpage, 'id') + title = remove_end(self._html_search_regex( + r'([^<]+)', webpage, 'title'), ' - Hell Porno') - ext = self._html_search_regex( - r'postfix:\s*\'([^\']+)\'', webpage, 'ext')[1:] + flashvars = self._parse_json(self._search_regex( + r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'), + display_id, transform_source=js_to_json) - video_url = self._html_search_regex( - r'video_url:\s*\'([^\']+)\'', webpage, 'video_url') + video_id = flashvars.get('video_id') + thumbnail = flashvars.get('preview_url') + ext = flashvars.get('postfix', '.mp4')[1:] - title = self._html_search_regex( - r'([^<]+)\s*-\s*Hell Porno', webpage, 'title') - - thumbnail = self._html_search_regex( - r'preview_url:\s*\'([^\']+)\'', - webpage, 'thumbnail', fatal=False) + formats = [] + for video_url_key in ['video_url', 'video_alt_url']: + video_url = flashvars.get(video_url_key) + if not video_url: + continue + video_text = flashvars.get('%s_text' % video_url_key) + fmt = { + 'url': video_url, + 'ext': ext, + 'format_id': video_text, + } + m = re.search(r'^(?P\d+)[pP]', video_text) + if m: + fmt['height'] = int(m.group('height')) + formats.append(fmt) + self._sort_formats(formats) categories = self._html_search_meta( 'keywords', webpage, 'categories', default='').split(',') @@ -43,10 +63,9 @@ class HellPornoIE(InfoExtractor): return { 'id': video_id, 'display_id': display_id, - 'url': video_url, 'title': title, - 'ext': ext, 'thumbnail': thumbnail, 'categories': categories, 'age_limit': 18, + 'formats': formats, }