1bed39e · searx · git.iko.soy

searx/engines/dailymotion.py+2−2

compare with master

unifiedsplit

@@ -15,7 +15,7 @@

15from json import loads

16from datetime import datetime

17from searx.url_utils import urlencode

18−from searx.utils import match_language

18+from searx.utils import match_language, html_to_text

19

20# engine dependent config

21categories = ['videos']

@@ -59,7 +59,7 @@ def response(resp):

59 for res in search_res['list']:

60 title = res['title']

61 url = res['url']

62− content = res['description']

62+ content = html_to_text(res['description'])

63 thumbnail = res['thumbnail_360_url']

64 publishedDate = datetime.fromtimestamp(res['created_time'], None)

65 embedded = embedded_url.format(videoid=res['id'])

searx/engines/google_videos.py+11−9

@@ -75,15 +75,17 @@ def response(resp):

75

76 # get thumbnails

77 script = str(dom.xpath('//script[contains(., "_setImagesSrc")]')[0].text)

78− id = result.xpath('.//div[@class="s"]//img/@id')[0]

78+ ids = result.xpath('.//div[@class="s"]//img/@id')

79+ if len(ids) > 0:

80+ thumbnails_data = \

79− thumbnails_data = re.findall('s=\'(.*?)(?:\\\\[a-z,1-9,\\\\]+\'|\')\;var ii=\[(?:|[\'vidthumb\d+\',]+)\'' + id,

81+ re.findall('s=\'(.*?)(?:\\\\[a-z,1-9,\\\\]+\'|\')\;var ii=\[(?:|[\'vidthumb\d+\',]+)\'' + ids[0],

80− script)

82+ script)

81− tmp = []

83+ tmp = []

82− if len(thumbnails_data) != 0:

84+ if len(thumbnails_data) != 0:

83− tmp = re.findall('(data:image/jpeg;base64,[a-z,A-Z,0-9,/,\+]+)', thumbnails_data[0])

85+ tmp = re.findall('(data:image/jpeg;base64,[a-z,A-Z,0-9,/,\+]+)', thumbnails_data[0])

84− thumbnail = ''

86+ thumbnail = ''

85− if len(tmp) != 0:

87+ if len(tmp) != 0:

86− thumbnail = tmp[-1]

88+ thumbnail = tmp[-1]

87

89

88 # append result

90 # append result

89 results.append({'url': url,

91 results.append({'url': url,

searx/engines/youtube_noapi.py+9−6

@@ -67,12 +67,8 @@ def response(resp):

67 if videoid is not None:

68 url = base_youtube_url + videoid

69 thumbnail = 'https://i.ytimg.com/vi/' + videoid + '/hqdefault.jpg'

70− title = video.get('title', {}).get('simpleText', videoid)

70+ title = get_text_from_json(video.get('title', {}))

71− description_snippet = video.get('descriptionSnippet', {})

71+ content = get_text_from_json(video.get('descriptionSnippet', {}))

72− if 'runs' in description_snippet:

73− content = reduce(lambda a, b: a + b.get('text', ''), description_snippet.get('runs'), '')

74− else:

75− content = description_snippet.get('simpleText', '')

76 embedded = embedded_url.format(videoid=videoid)

72 embedded = embedded_url.format(videoid=videoid)

77

73

78 # append result

74 # append result

@@ -85,3 +81,10 @@ def response(resp):

85

81

86 # return results

82 # return results

87 return results

83 return results

84+

85+

86+def get_text_from_json(element):

87+ if 'runs' in element:

88+ return reduce(lambda a, b: a + b.get('text', ''), element.get('runs'), '')

89+ else:

90+ return element.get('simpleText', '')