summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorNoémi Ványi <kvch@users.noreply.github.com>2019-01-05 18:08:05 +0100
committerGitHub <noreply@github.com>2019-01-05 18:08:05 +0100
commitabcbcec0b5ab9a3108ccc972876fdb60c7911e7a (patch)
tree65997b07ea9b2292662f9d5453c6fd388d10845a
parent899ba5d6dee82faacb572b4d9bc4c58570628531 (diff)
parent2456b8f57199b0479b063fa3dfb16a585c6a40ed (diff)
downloadsearxng-abcbcec0b5ab9a3108ccc972876fdb60c7911e7a.tar.gz
searxng-abcbcec0b5ab9a3108ccc972876fdb60c7911e7a.zip
Merge pull request #1444 from Venca24/devel_google_videos
[fix] google videos engine
-rw-r--r--searx/engines/google_videos.py24
-rw-r--r--tests/unit/engines/test_google_videos.py27
2 files changed, 41 insertions, 10 deletions
diff --git a/searx/engines/google_videos.py b/searx/engines/google_videos.py
index 310b31490..9a41b2dfa 100644
--- a/searx/engines/google_videos.py
+++ b/searx/engines/google_videos.py
@@ -7,7 +7,7 @@
@using-api no
@results HTML
@stable no
- @parse url, title, content
+ @parse url, title, content, thumbnail
"""
from datetime import date, timedelta
@@ -15,7 +15,7 @@ from json import loads
from lxml import html
from searx.engines.xpath import extract_text
from searx.url_utils import urlencode
-
+import re
# engine dependent config
categories = ['videos']
@@ -25,7 +25,7 @@ time_range_support = True
number_of_results = 10
search_url = 'https://www.google.com/search'\
- '?{query}'\
+ '?q={query}'\
'&tbm=vid'\
'&{search_options}'
time_range_attr = "qdr:{range}"
@@ -69,15 +69,27 @@ def response(resp):
# parse results
for result in dom.xpath('//div[@class="g"]'):
- title = extract_text(result.xpath('.//h3/a'))
- url = result.xpath('.//h3/a/@href')[0]
+ title = extract_text(result.xpath('.//h3'))
+ url = result.xpath('.//div[@class="r"]/a/@href')[0]
content = extract_text(result.xpath('.//span[@class="st"]'))
+ # get thumbnails
+ script = str(dom.xpath('//script[contains(., "_setImagesSrc")]')[0].text)
+ id = result.xpath('.//div[@class="s"]//img/@id')[0]
+ thumbnails_data = re.findall('s=\'(.*?)(?:\\\\[a-z,1-9,\\\\]+\'|\')\;var ii=\[(?:|[\'vidthumb\d+\',]+)\'' + id,
+ script)
+ tmp = []
+ if len(thumbnails_data) != 0:
+ tmp = re.findall('(data:image/jpeg;base64,[a-z,A-Z,0-9,/,\+]+)', thumbnails_data[0])
+ thumbnail = ''
+ if len(tmp) != 0:
+ thumbnail = tmp[-1]
+
# append result
results.append({'url': url,
'title': title,
'content': content,
- 'thumbnail': '',
+ 'thumbnail': thumbnail,
'template': 'videos.html'})
return results
diff --git a/tests/unit/engines/test_google_videos.py b/tests/unit/engines/test_google_videos.py
index a48e9a755..3b7edf373 100644
--- a/tests/unit/engines/test_google_videos.py
+++ b/tests/unit/engines/test_google_videos.py
@@ -30,16 +30,34 @@ class TestGoogleVideosEngine(SearxTestCase):
<div>
<div>
<div class="g">
- <div>
- <h3><a href="url_1">Title 1</h3>
+ <div class="r">
+ <a href="url_1"><h3>Title 1</h3></a>
+ </div>
+ <div class="s">
+ <div>
+ <a>
+ <g-img>
+ <img id="vidthumb1">
+ </g-img>
+ </a>
+ </div>
</div>
<div>
<span class="st">Content 1</span>
</div>
</div>
<div class="g">
- <div>
- <h3><a href="url_2">Title 2</h3>
+ <div class="r">
+ <a href="url_2"><h3>Title 2</h3></a>
+ </div>
+ <div class="s">
+ <div>
+ <a>
+ <g-img>
+ <img id="vidthumb2">
+ </g-img>
+ </a>
+ </div>
</div>
<div>
<span class="st">Content 2</span>
@@ -47,6 +65,7 @@ class TestGoogleVideosEngine(SearxTestCase):
</div>
</div>
</div>
+ <script>function _setImagesSrc(c,d,e){}</script>
"""
response = mock.Mock(text=html)
results = google_videos.response(response)