From f3517569f60345a3948ce145fb603fe2a71b2d6f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com>
Date: Fri, 28 Oct 2016 23:19:59 +0700
Subject: [PATCH] [gvsearch] Modernize and fix page result request (closes
#11051)
---
youtube_dl/extractor/googlesearch.py | 18 +++++++++---------
1 file changed, 9 insertions(+), 9 deletions(-)
diff --git a/youtube_dl/extractor/googlesearch.py b/youtube_dl/extractor/googlesearch.py
index 498304cb2..5279fa807 100644
--- a/youtube_dl/extractor/googlesearch.py
+++ b/youtube_dl/extractor/googlesearch.py
@@ -4,9 +4,6 @@ import itertools
import re
from .common import SearchInfoExtractor
-from ..compat import (
- compat_urllib_parse,
-)
class GoogleSearchIE(SearchInfoExtractor):
@@ -34,13 +31,16 @@ class GoogleSearchIE(SearchInfoExtractor):
}
for pagenum in itertools.count():
- result_url = (
- 'http://www.google.com/search?tbm=vid&q=%s&start=%s&hl=en'
- % (compat_urllib_parse.quote_plus(query), pagenum * 10))
-
webpage = self._download_webpage(
- result_url, 'gvsearch:' + query,
- note='Downloading result page ' + str(pagenum + 1))
+ 'http://www.google.com/search',
+ 'gvsearch:' + query,
+ note='Downloading result page %s' % (pagenum + 1),
+ query={
+ 'tbm': 'vid',
+ 'q': query,
+ 'start': pagenum * 10,
+ 'hl': 'en',
+ })
for hit_idx, mobj in enumerate(re.finditer(
r'<h3 class="r"><a href="([^"]+)"', webpage)):