diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 62819ddcf..1a39c25c5 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1029,6 +1029,7 @@ from .safari import ( SafariApiIE, SafariCourseIE, ) +from .samplefocus import SampleFocusIE from .sapo import SapoIE from .savefrom import SaveFromIE from .sbs import SBSIE diff --git a/youtube_dl/extractor/samplefocus.py b/youtube_dl/extractor/samplefocus.py new file mode 100644 index 000000000..806c3c354 --- /dev/null +++ b/youtube_dl/extractor/samplefocus.py @@ -0,0 +1,100 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + extract_attributes, + get_element_by_attribute, + int_or_none, +) + + +class SampleFocusIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?samplefocus\.com/samples/(?P[^/?&#]+)' + _TESTS = [{ + 'url': 'https://samplefocus.com/samples/lil-peep-sad-emo-guitar', + 'md5': '48c8d62d60be467293912e0e619a5120', + 'info_dict': { + 'id': '40316', + 'display_id': 'lil-peep-sad-emo-guitar', + 'ext': 'mp3', + 'title': 'Lil Peep Sad Emo Guitar', + 'thumbnail': r're:^https?://.+\.png', + 'license': 'Standard License', + 'uploader': 'CapsCtrl', + 'uploader_id': 'capsctrl', + 'like_count': int, + 'comment_count': int, + 'categories': ['Samples', 'Guitar', 'Electric guitar'], + }, + }, { + 'url': 'https://samplefocus.com/samples/dababy-style-bass-808', + 'only_matching': True + }, { + 'url': 'https://samplefocus.com/samples/young-chop-kick', + 'only_matching': True + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + sample_id = self._search_regex( + r']+id=(["\'])sample_id\1[^>]+value=(?:["\'])(?P\d+)', + webpage, 'sample id', group='id') + + title = self._og_search_title(webpage, fatal=False) or self._html_search_regex( + r'

(.+?)

', webpage, 'title') + + mp3_url = self._search_regex( + r']+id=(["\'])sample_mp3\1[^>]+value=(["\'])(?P(?:(?!\2).)+)', + webpage, 'mp3', fatal=False, group='url') or extract_attributes(self._search_regex( + r']+itemprop=(["\'])contentUrl\1[^>]*>', + webpage, 'mp3 url', group=0))['content'] + + thumbnail = self._og_search_thumbnail(webpage) or self._html_search_regex( + r']+class=(?:["\'])waveform responsive-img[^>]+src=(["\'])(?P(?:(?!\1).)+)', + webpage, 'mp3', fatal=False, group='url') + + comments = [] + for author_id, author, body in re.findall(r'(?s)]+class="comment-author">]+href="/users/([^"]+)">([^"]+).+?]+class="comment-body">([^>]+)

', webpage): + comments.append({ + 'author': author, + 'author_id': author_id, + 'text': body, + }) + + uploader_id = uploader = None + mobj = re.search(r'>By ]+href="/users/([^"]+)"[^>]*>([^<]+)', webpage) + if mobj: + uploader_id, uploader = mobj.groups() + + breadcrumb = get_element_by_attribute('typeof', 'BreadcrumbList', webpage) + categories = [] + if breadcrumb: + for _, name in re.findall(r']+property=(["\'])name\1[^>]*>([^<]+)', breadcrumb): + categories.append(name) + + def extract_count(klass): + return int_or_none(self._html_search_regex( + r']+class=(?:["\'])?%s-count[^>]*>(\d+)' % klass, + webpage, klass, fatal=False)) + + return { + 'id': sample_id, + 'title': title, + 'url': mp3_url, + 'display_id': display_id, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'license': self._html_search_regex( + r']+href=(["\'])/license\1[^>]*>(?P[^<]+)<', + webpage, 'license', fatal=False, group='license'), + 'uploader_id': uploader_id, + 'like_count': extract_count('sample-%s-favorites' % sample_id), + 'comment_count': extract_count('comments'), + 'comments': comments, + 'categories': categories, + }