aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/varzesh3.py
diff options
context:
space:
mode:
authorYen Chi Hsuan <yan12125@gmail.com>2016-04-16 17:13:22 +0800
committerYen Chi Hsuan <yan12125@gmail.com>2016-04-16 17:13:22 +0800
commitee94e7e66d8c715f0df29c22642e51cb56c612b9 (patch)
tree5f64e203d2c47655cc483f528abaac2ef766cd9c /youtube_dl/extractor/varzesh3.py
parent759e37c9e661d962c2318d173f9c99264c1e7e2b (diff)
downloadyoutube-dl-ee94e7e66d8c715f0df29c22642e51cb56c612b9.tar.xz
[varzesh3] Fix metadata extraction (closes #9197)
Diffstat (limited to 'youtube_dl/extractor/varzesh3.py')
-rw-r--r--youtube_dl/extractor/varzesh3.py47
1 files changed, 40 insertions, 7 deletions
diff --git a/youtube_dl/extractor/varzesh3.py b/youtube_dl/extractor/varzesh3.py
index 9369abaf8..438bb580c 100644
--- a/youtube_dl/extractor/varzesh3.py
+++ b/youtube_dl/extractor/varzesh3.py
@@ -2,11 +2,19 @@
from __future__ import unicode_literals
from .common import InfoExtractor
+from ..compat import (
+ compat_urllib_parse_urlparse,
+ compat_parse_qs,
+)
+from ..utils import (
+ clean_html,
+ remove_start,
+)
class Varzesh3IE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?video\.varzesh3\.com/(?:[^/]+/)+(?P<id>[^/]+)/?'
- _TEST = {
+ _TESTS = [{
'url': 'http://video.varzesh3.com/germany/bundesliga/5-%D9%88%D8%A7%DA%A9%D9%86%D8%B4-%D8%A8%D8%B1%D8%AA%D8%B1-%D8%AF%D8%B1%D9%88%D8%A7%D8%B2%D9%87%E2%80%8C%D8%A8%D8%A7%D9%86%D8%A7%D9%86%D8%9B%D9%87%D9%81%D8%AA%D9%87-26-%D8%A8%D9%88%D9%86%D8%AF%D8%B3/',
'md5': '2a933874cb7dce4366075281eb49e855',
'info_dict': {
@@ -15,8 +23,18 @@ class Varzesh3IE(InfoExtractor):
'title': '۵ واکنش برتر دروازه‌بانان؛هفته ۲۶ بوندسلیگا',
'description': 'فصل ۲۰۱۵-۲۰۱۴',
'thumbnail': 're:^https?://.*\.jpg$',
- }
- }
+ },
+ 'skip': 'HTTP 404 Error',
+ }, {
+ 'url': 'http://video.varzesh3.com/video/112785/%D8%AF%D9%84%D9%87-%D8%B9%D9%84%DB%8C%D8%9B-%D8%B3%D8%AA%D8%A7%D8%B1%D9%87-%D9%86%D9%88%D8%B8%D9%87%D9%88%D8%B1-%D9%84%DB%8C%DA%AF-%D8%A8%D8%B1%D8%AA%D8%B1-%D8%AC%D8%B2%DB%8C%D8%B1%D9%87',
+ 'info_dict': {
+ 'id': '112785',
+ 'ext': 'mp4',
+ 'title': 'دله علی؛ ستاره نوظهور لیگ برتر جزیره',
+ 'description': 'فوتبال 120',
+ },
+ 'expected_warnings': ['description'],
+ }]
def _real_extract(self, url):
display_id = self._match_id(url)
@@ -26,15 +44,30 @@ class Varzesh3IE(InfoExtractor):
video_url = self._search_regex(
r'<source[^>]+src="([^"]+)"', webpage, 'video url')
- title = self._og_search_title(webpage)
+ title = remove_start(self._html_search_regex(
+ r'<title>([^<]+)</title>', webpage, 'title'), 'ویدیو ورزش 3 | ')
+
description = self._html_search_regex(
r'(?s)<div class="matn">(.+?)</div>',
- webpage, 'description', fatal=False)
- thumbnail = self._og_search_thumbnail(webpage)
+ webpage, 'description', default=None)
+ if description is None:
+ description = clean_html(self._html_search_meta('description', webpage))
+
+ thumbnail = self._og_search_thumbnail(webpage, default=None)
+ if thumbnail is None:
+ fb_sharer_url = self._search_regex(
+ r'<a[^>]+href="(https?://www\.facebook\.com/sharer/sharer\.php?[^"]+)"',
+ webpage, 'facebook sharer URL', fatal=False)
+ sharer_params = compat_parse_qs(compat_urllib_parse_urlparse(fb_sharer_url).query)
+ thumbnail = sharer_params.get('p[images][0]', [None])[0]
video_id = self._search_regex(
r"<link[^>]+rel='(?:canonical|shortlink)'[^>]+href='/\?p=([^']+)'",
- webpage, display_id, default=display_id)
+ webpage, display_id, default=None)
+ if video_id is None:
+ video_id = self._search_regex(
+ 'var\s+VideoId\s*=\s*(\d+);', webpage, 'video id',
+ default=display_id)
return {
'url': video_url,