74b6be3 · searx · git.iko.soy

searx/engines/duckduckgo.py+4−1

compare with master

unifiedsplit

@@ -1,8 +1,11 @@

1from json import loads

2+from urllib import urlencode

2

3

4+url = 'https://duckduckgo.com/'

5+search_url = url + 'd.js?{query}&l=us-en&p=1&s=0'

3

6

4def request(query, params):

7def request(query, params):

5− params['url'] = 'https://duckduckgo.com/d.js?q=%s&l=us-en&p=1&s=0' % query

8+ params['url'] = search_url.format(query=urlencode({'q': query}))

6 return params

9 return params

7

10

8

11

searx/engines/duckduckgo_definitions.py+4−1

@@ -1,7 +1,10 @@

1import json

2+from urllib import urlencode

3+

4+url = 'http://api.duckduckgo.com/?{query}&format=json&pretty=0'

2

5

3def request(query, params):

6def request(query, params):

4− params['url'] = 'http://api.duckduckgo.com/?q=%s&format=json&pretty=0' % query

7+ params['url'] = url.format(query=urlencode({'q': query}))

5 return params

8 return params

6

9

7

10

searx/engines/flickr.py+6−8

@@ -1,18 +1,16 @@

1#!/usr/bin/env python

2

3−from urllib import quote

3+from urllib import urlencode

4from lxml import html

5from urlparse import urljoin

6

7categories = ['images']

8

9−base_url = 'https://secure.flickr.com/'

9+url = 'https://secure.flickr.com/'

10−search_url = base_url+'search/?q='

10+search_url = url+'search/?q={query}'

11

12def request(query, params):

13− global search_url

14− query = quote(query.replace(' ', '+'), safe='+')

15− params['url'] = search_url + query

13+ params['url'] = search_url.format(query=urlencode({'q': query}))

16 return params

14 return params

17

15

18def response(resp):

16def response(resp):

@@ -20,11 +18,11 @@ def response(resp):

20 results = []

18 results = []

21 dom = html.fromstring(resp.text)

19 dom = html.fromstring(resp.text)

22 for result in dom.xpath('//div[@id="thumbnails"]//a[@class="rapidnofollow photo-click" and @data-track="photo-click"]'):

20 for result in dom.xpath('//div[@id="thumbnails"]//a[@class="rapidnofollow photo-click" and @data-track="photo-click"]'):

23− url = urljoin(base_url, result.attrib.get('href'))

21+ href = urljoin(url, result.attrib.get('href'))

24 img = result.xpath('.//img')[0]

22 img = result.xpath('.//img')[0]

25 title = img.attrib.get('alt', '')

23 title = img.attrib.get('alt', '')

26 img_src = img.attrib.get('data-defer-src')

24 img_src = img.attrib.get('data-defer-src')

27 if not img_src:

25 if not img_src:

28 continue

26 continue

29− results.append({'url': url, 'title': title, 'img_src': img_src, 'template': 'images.html'})

27+ results.append({'url': href, 'title': title, 'img_src': img_src, 'template': 'images.html'})

30 return results

28 return results

searx/engines/github.py+2−2

@@ -4,11 +4,11 @@ from cgi import escape

4

5categories = ['it']

6

7−search_url = 'https://api.github.com/search/repositories?sort=stars&order=desc&'

7+search_url = 'https://api.github.com/search/repositories?sort=stars&order=desc&{query}'

8

9def request(query, params):

10 global search_url

11− params['url'] = search_url + urlencode({'q': query})

11+ params['url'] = search_url.format(query=urlencode({'q': query}))

12 params['headers']['Accept'] = 'application/vnd.github.preview.text-match+json'

13 return params

14

searx/engines/google_images.py+4−5

@@ -5,15 +5,14 @@ from json import loads

5

6categories = ['images']

7

8+url = 'https://ajax.googleapis.com/'

8−search_url = 'https://ajax.googleapis.com/ajax/services/search/images?v=1.0&start=0&rsz=large&safe=off&filter=off&'

9+search_url = url + 'ajax/services/search/images?v=1.0&start=0&rsz=large&safe=off&filter=off&{query}'

9

10

10def request(query, params):

11def request(query, params):

11− global search_url

12 params['url'] = search_url + urlencode({'q': query})

13 return params

14

15def response(resp):

16− global base_url

17 results = []

16 results = []

18 search_res = loads(resp.text)

17 search_res = loads(resp.text)

19 if not search_res.get('responseData'):

18 if not search_res.get('responseData'):

@@ -21,9 +20,9 @@ def response(resp):

21 if not search_res['responseData'].get('results'):

20 if not search_res['responseData'].get('results'):

22 return []

21 return []

23 for result in search_res['responseData']['results']:

22 for result in search_res['responseData']['results']:

24− url = result['originalContextUrl']

23+ href = result['originalContextUrl']

25 title = result['title']

24 title = result['title']

26 if not result['url']:

25 if not result['url']:

27 continue

26 continue

28− results.append({'url': url, 'title': title, 'content': '', 'img_src': result['url'], 'template': 'images.html'})

27+ results.append({'url': href, 'title': title, 'content': '', 'img_src': result['url'], 'template': 'images.html'})

29 return results

28 return results

searx/engines/piratebay.py+5−8

@@ -5,21 +5,18 @@ from urllib import quote

5

6categories = ['videos', 'music']

7

8−base_url = 'https://thepiratebay.sx/'

8+url = 'https://thepiratebay.sx/'

9−search_url = base_url + 'search/{search_term}/0/99/{search_type}'

9+search_url = url + 'search/{search_term}/0/99/{search_type}'

10search_types = {'videos': '200'

11 ,'music' : '100'

12 }

13

14def request(query, params):

15− global search_url, search_types

16− # 200 is the video category

17 params['url'] = search_url.format(search_term=quote(query), search_type=search_types.get(params['category']))

15 params['url'] = search_url.format(search_term=quote(query), search_type=search_types.get(params['category']))

18 return params

16 return params

19

17

20

18

21def response(resp):

19def response(resp):

22− global base_url

23 results = []

20 results = []

24 dom = html.fromstring(resp.text)

21 dom = html.fromstring(resp.text)

25 search_res = dom.xpath('//table[@id="searchResult"]//tr')

22 search_res = dom.xpath('//table[@id="searchResult"]//tr')

@@ -27,12 +24,12 @@ def response(resp):

27 return results

24 return results

28 for result in search_res[1:]:

25 for result in search_res[1:]:

29 link = result.xpath('.//div[@class="detName"]//a')[0]

26 link = result.xpath('.//div[@class="detName"]//a')[0]

30− url = urljoin(base_url, link.attrib.get('href'))

27+ href = urljoin(url, link.attrib.get('href'))

31 title = ' '.join(link.xpath('.//text()'))

28 title = ' '.join(link.xpath('.//text()'))

32 content = escape(' '.join(result.xpath('.//font[@class="detDesc"]//text()')))

29 content = escape(' '.join(result.xpath('.//font[@class="detDesc"]//text()')))

33 seed, leech = result.xpath('.//td[@align="right"]/text()')[:2]

30 seed, leech = result.xpath('.//td[@align="right"]/text()')[:2]

34 content += '<br />Seed: %s, Leech: %s' % (seed, leech)

31 content += '<br />Seed: %s, Leech: %s' % (seed, leech)

35 magnetlink = result.xpath('.//a[@title="Download this torrent using magnet"]')[0]

32 magnetlink = result.xpath('.//a[@title="Download this torrent using magnet"]')[0]

36− content += '<br /><a href="%s">magnet link</a>' % urljoin(base_url, magnetlink.attrib['href'])

33+ content += '<br /><a href="%s">magnet link</a>' % urljoin(url, magnetlink.attrib['href'])

37− results.append({'url': url, 'title': title, 'content': content})

34+ results.append({'url': href, 'title': title, 'content': content})

38 return results

35 return results

searx/engines/soundcloud.py+4−2

@@ -1,13 +1,15 @@

1from json import loads

2+from urllib import urlencode

2

3

3categories = ['music']

4categories = ['music']

4

5

5guest_client_id = 'b45b1aa10f1ac2941910a7f0d10f8e28'

6guest_client_id = 'b45b1aa10f1ac2941910a7f0d10f8e28'

7+url = 'https://api.soundcloud.com/'

6−search_url = 'https://api.soundcloud.com/search?q=%s&facet=model&limit=10&offset=0&linked_partitioning=1&client_id='+guest_client_id

8+search_url = url + 'search?{query}&facet=model&limit=20&offset=0&linked_partitioning=1&client_id='+guest_client_id

7

9

8def request(query, params):

10def request(query, params):

9 global search_url

11 global search_url

10− params['url'] = search_url % query

12+ params['url'] = search_url.format(query=urlencode({'q': query}))

11 return params

13 return params

12

14

13

15

searx/engines/stackoverflow.py+4−6

@@ -5,23 +5,21 @@ from urllib import urlencode

5

6categories = ['it']

7

8−base_url = 'http://stackoverflow.com/'

8+url = 'http://stackoverflow.com/'

9−search_url = base_url+'search?'

9+search_url = url+'search?'

10

11def request(query, params):

12− global search_url

13 params['url'] = search_url + urlencode({'q': query})

12 params['url'] = search_url + urlencode({'q': query})

14 return params

13 return params

15

14

16

15

17def response(resp):

16def response(resp):

18− global base_url

19 results = []

17 results = []

20 dom = html.fromstring(resp.text)

18 dom = html.fromstring(resp.text)

21 for result in dom.xpath('//div[@class="question-summary search-result"]'):

19 for result in dom.xpath('//div[@class="question-summary search-result"]'):

22 link = result.xpath('.//div[@class="result-link"]//a')[0]

20 link = result.xpath('.//div[@class="result-link"]//a')[0]

23− url = urljoin(base_url, link.attrib.get('href'))

21+ href = urljoin(url, link.attrib.get('href'))

24 title = ' '.join(link.xpath('.//text()'))

22 title = ' '.join(link.xpath('.//text()'))

25 content = escape(' '.join(result.xpath('.//div[@class="excerpt"]//text()')))

23 content = escape(' '.join(result.xpath('.//div[@class="excerpt"]//text()')))

26− results.append({'url': url, 'title': title, 'content': content})

24+ results.append({'url': href, 'title': title, 'content': content})

27 return results

25 return results

searx/engines/youtube.py+3−6

@@ -1,15 +1,12 @@

1from json import loads

2−from urllib import quote

2+from urllib import urlencode

3

4categories = ['videos']

5

6−search_url = 'https://gdata.youtube.com/feeds/api/videos?alt=json&q='

6+search_url = 'https://gdata.youtube.com/feeds/api/videos?alt=json&{query}'

7

8def request(query, params):

9− global search_url

10− query = quote(query.replace(' ', '+'), safe='+')

11− params['url'] = search_url + query

9+ params['url'] = search_url.format(query=urlencode({'q': query}))

12−

13 return params

10 return params

14

11

15

12