cf26aba · searx · git.iko.soy

7 @using-api no

8 @results HTML

9 @stable no

10− @parse url, title, content

10+ @parse url, title, content, thumbnail

11"""

12

13from datetime import date, timedelta

14from json import loads

15from lxml import html

16+from searx.engines import logger

16from searx.engines.xpath import extract_text

17from searx.engines.xpath import extract_text

17from searx.url_utils import urlencode

18from searx.url_utils import urlencode

18−

19+import re

19

20

20# engine dependent config

21# engine dependent config

21categories = ['videos']

22categories = ['videos']

73 url = result.xpath('.//div[@class="r"]/a/@href')[0]

74 url = result.xpath('.//div[@class="r"]/a/@href')[0]

74 content = extract_text(result.xpath('.//span[@class="st"]'))

75 content = extract_text(result.xpath('.//span[@class="st"]'))

75

76

77+ # get thumbnails

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

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

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

81+ script)

82+ logger.debug('google video engine: ' + id + ' matched ' + str(len(thumbnails_data)) + ' times (thumbnail)')

83+ tmp = []

84+ if len(thumbnails_data) != 0:

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

86+ thumbnail = ''

87+ if len(tmp) != 0:

88+ thumbnail = tmp[-1]

89+

76 # append result

90 # append result

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

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

78 'title': title,

92 'title': title,

79 'content': content,

93 'content': content,

80− 'thumbnail': '',

94+ 'thumbnail': thumbnail,

81 'template': 'videos.html'})

95 'template': 'videos.html'})

82

96

83 return results

97 return results