diff options
Diffstat (limited to 'youtube_dl/extractor/eporner.py')
| -rw-r--r-- | youtube_dl/extractor/eporner.py | 38 |
1 files changed, 27 insertions, 11 deletions
diff --git a/youtube_dl/extractor/eporner.py b/youtube_dl/extractor/eporner.py index f3734e9f8..bfecd3a41 100644 --- a/youtube_dl/extractor/eporner.py +++ b/youtube_dl/extractor/eporner.py @@ -4,18 +4,19 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( encode_base_n, ExtractorError, int_or_none, + merge_dicts, parse_duration, str_to_int, + url_or_none, ) class EpornerIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\w+)(?:/(?P<display_id>[\w-]+))?' + _VALID_URL = r'https?://(?:www\.)?eporner\.com/(?:(?:hd-porn|embed)/|video-)(?P<id>\w+)(?:/(?P<display_id>[\w-]+))?' _TESTS = [{ 'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/', 'md5': '39d486f046212d8e1b911c52ab4691f8', @@ -24,10 +25,16 @@ class EpornerIE(InfoExtractor): 'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video', 'ext': 'mp4', 'title': 'Infamous Tiffany Teen Strip Tease Video', + 'description': 'md5:764f39abf932daafa37485eb46efa152', + 'timestamp': 1232520922, + 'upload_date': '20090121', 'duration': 1838, 'view_count': int, 'age_limit': 18, }, + 'params': { + 'proxy': '127.0.0.1:8118' + } }, { # New (May 2016) URL layout 'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0/Star-Wars-XXX-Parody/', @@ -35,6 +42,12 @@ class EpornerIE(InfoExtractor): }, { 'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0', 'only_matching': True, + }, { + 'url': 'http://www.eporner.com/embed/3YRUtzMcWn0', + 'only_matching': True, + }, { + 'url': 'https://www.eporner.com/video-FJsA19J3Y3H/one-of-the-greats/', + 'only_matching': True, }] def _real_extract(self, url): @@ -44,10 +57,10 @@ class EpornerIE(InfoExtractor): webpage, urlh = self._download_webpage_handle(url, display_id) - video_id = self._match_id(compat_str(urlh.geturl())) + video_id = self._match_id(urlh.geturl()) hash = self._search_regex( - r'hash\s*:\s*["\']([\da-f]{32})', webpage, 'hash') + r'hash\s*[:=]\s*["\']([\da-f]{32})', webpage, 'hash') title = self._og_search_title(webpage, default=None) or self._html_search_regex( r'<title>(.+?) - EPORNER', webpage, 'title') @@ -79,8 +92,8 @@ class EpornerIE(InfoExtractor): for format_id, format_dict in formats_dict.items(): if not isinstance(format_dict, dict): continue - src = format_dict.get('src') - if not isinstance(src, compat_str) or not src.startswith('http'): + src = url_or_none(format_dict.get('src')) + if not src or not src.startswith('http'): continue if kind == 'hls': formats.extend(self._extract_m3u8_formats( @@ -100,12 +113,15 @@ class EpornerIE(InfoExtractor): }) self._sort_formats(formats) - duration = parse_duration(self._html_search_meta('duration', webpage)) + json_ld = self._search_json_ld(webpage, display_id, default={}) + + duration = parse_duration(self._html_search_meta( + 'duration', webpage, default=None)) view_count = str_to_int(self._search_regex( - r'id="cinemaviews">\s*([0-9,]+)\s*<small>views', - webpage, 'view count', fatal=False)) + r'id=["\']cinemaviews1["\'][^>]*>\s*([0-9,]+)', + webpage, 'view count', default=None)) - return { + return merge_dicts(json_ld, { 'id': video_id, 'display_id': display_id, 'title': title, @@ -113,4 +129,4 @@ class EpornerIE(InfoExtractor): 'view_count': view_count, 'formats': formats, 'age_limit': 18, - } + }) |