From 58bb4402834bc3ed5ec0046ee5a8d71e56532134 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 13 May 2017 21:51:58 +0700 Subject: [PATCH] [extractor/generic] Extract wistia embed code into separate method --- youtube_dl/extractor/generic.py | 30 +++++------------------------- youtube_dl/extractor/wistia.py | 22 ++++++++++++++++++++++ 2 files changed, 27 insertions(+), 25 deletions(-) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 635043c9e..8f9097945 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -88,6 +88,7 @@ from .limelight import LimelightBaseIE from .anvato import AnvatoIE from .washingtonpost import WashingtonPostIE +from .wistia import WistiaIE class GenericIE(InfoExtractor): @@ -2111,36 +2112,15 @@ def _real_extract(self, url): playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p) # Look for embedded Wistia player - match = re.search( - r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage) - if match: - embed_url = self._proto_relative_url( - unescapeHTML(match.group('url'))) + wistia_url = WistiaIE._extract_url(webpage) + if wistia_url: return { '_type': 'url_transparent', - 'url': embed_url, - 'ie_key': 'Wistia', + 'url': self._proto_relative_url(wistia_url), + 'ie_key': WistiaIE.ie_key(), 'uploader': video_uploader, } - match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P[^"\']+)', webpage) - if match: - return { - '_type': 'url_transparent', - 'url': 'wistia:%s' % match.group('id'), - 'ie_key': 'Wistia', - 'uploader': video_uploader, - } - - match = re.search( - r'''(?sx) - ]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*? - ]+class=(["']).*?\bwistia_async_(?P[a-z0-9]+)\b.*?\2 - ''', webpage) - if match: - return self.url_result(self._proto_relative_url( - 'wistia:%s' % match.group('id')), 'Wistia') - # Look for SVT player svt_url = SVTIE._extract_url(webpage) if svt_url: diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py index c634b8dec..2182d6fd4 100644 --- a/youtube_dl/extractor/wistia.py +++ b/youtube_dl/extractor/wistia.py @@ -1,10 +1,13 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( ExtractorError, int_or_none, float_or_none, + unescapeHTML, ) @@ -34,6 +37,25 @@ class WistiaIE(InfoExtractor): 'only_matching': True, }] + @staticmethod + def _extract_url(webpage): + match = re.search( + r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage) + if match: + return unescapeHTML(match.group('url')) + + match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P[^"\']+)', webpage) + if match: + return 'wistia:%s' % match.group('id') + + match = re.search( + r'''(?sx) + ]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*? + ]+class=(["']).*?\bwistia_async_(?P[a-z0-9]+)\b.*?\2 + ''', webpage) + if match: + return 'wistia:%s' % match.group('id') + def _real_extract(self, url): video_id = self._match_id(url)