e23c8f9 · searx · git.iko.soy

searx/engines/bing_images.py+7

compare with master

unifiedsplit

@@ -24,11 +24,16 @@ import re

24categories = ['images']

25paging = True

26safesearch = True

27+time_range_support = True

27

28

28# search-url

29# search-url

29base_url = 'https://www.bing.com/'

30base_url = 'https://www.bing.com/'

30search_string = 'images/search?{query}&count=10&first={offset}'

31search_string = 'images/search?{query}&count=10&first={offset}'

32+time_range_string = '&qft=+filterui:age-lt{interval}'

31thumb_url = "https://www.bing.com/th?id={ihk}"

33thumb_url = "https://www.bing.com/th?id={ihk}"

34+time_range_dict = {'day': '1440',

35+ 'week': '10080',

36+ 'month': '43200'}

32

37

33# safesearch definitions

38# safesearch definitions

34safesearch_types = {2: 'STRICT',

39safesearch_types = {2: 'STRICT',

@@ -58,6 +63,8 @@ def request(query, params):

58 '&ADLT=' + safesearch_types.get(params['safesearch'], 'DEMOTE')

63 '&ADLT=' + safesearch_types.get(params['safesearch'], 'DEMOTE')

59

64

60 params['url'] = base_url + search_path

65 params['url'] = base_url + search_path

66+ if params['time_range'] in time_range_dict:

67+ params['url'] += time_range_string.format(interval=time_range_dict[params['time_range']])

61

68

62 return params

69 return params

63

70

searx/engines/bing_news.py+19−5

@@ -22,10 +22,15 @@ from searx.utils import list_get

22categories = ['news']

23paging = True

24language_support = True

25+time_range_support = True

25

26

26# search-url

27# search-url

27base_url = 'https://www.bing.com/'

28base_url = 'https://www.bing.com/'

28search_string = 'news/search?{query}&first={offset}&format=RSS'

29search_string = 'news/search?{query}&first={offset}&format=RSS'

30+search_string_with_time = 'news/search?{query}&first={offset}&qft=interval%3d"{interval}"&format=RSS'

31+time_range_dict = {'day': '7',

32+ 'week': '8',

33+ 'month': '9'}

29

34

30

35

31# remove click

36# remove click

@@ -46,6 +51,19 @@ def image_url_cleanup(url_string):

46 return url_string

51 return url_string

47

52

48

53

54+def _get_url(query, language, offset, time_range):

55+ if time_range in time_range_dict:

56+ search_path = search_string_with_time.format(

57+ query=urlencode({'q': query, 'setmkt': language}),

58+ offset=offset,

59+ interval=time_range_dict[time_range])

60+ else:

61+ search_path = search_string.format(

62+ query=urlencode({'q': query, 'setmkt': language}),

63+ offset=offset)

64+ return base_url + search_path

65+

66+

49# do search-request

67# do search-request

50def request(query, params):

68def request(query, params):

51 offset = (params['pageno'] - 1) * 10 + 1

69 offset = (params['pageno'] - 1) * 10 + 1

@@ -55,11 +73,7 @@ def request(query, params):

55 else:

73 else:

56 language = params['language'].replace('_', '-')

74 language = params['language'].replace('_', '-')

57

75

58− search_path = search_string.format(

76+ params['url'] = _get_url(query, language, offset, params['time_range'])

59− query=urlencode({'q': query, 'setmkt': language}),

60− offset=offset)

61−

62− params['url'] = base_url + search_path

63

77

64 return params

78 return params

65

79

searx/engines/flickr_noapi.py+14−3

@@ -14,6 +14,7 @@

14

15from urllib import urlencode

16from json import loads

17+from time import time

17import re

18import re

18from searx.engines import logger

19from searx.engines import logger

19

20

@@ -24,21 +25,31 @@ categories = ['images']

24

25

25url = 'https://www.flickr.com/'

26url = 'https://www.flickr.com/'

26search_url = url + 'search?{query}&page={page}'

27search_url = url + 'search?{query}&page={page}'

28+time_range_url = '&min_upload_date={start}&max_upload_date={end}'

27photo_url = 'https://www.flickr.com/photos/{userid}/{photoid}'

29photo_url = 'https://www.flickr.com/photos/{userid}/{photoid}'

28regex = re.compile(r"\"search-photos-lite-models\",\"photos\":(.*}),\"totalItems\":", re.DOTALL)

30regex = re.compile(r"\"search-photos-lite-models\",\"photos\":(.*}),\"totalItems\":", re.DOTALL)

29image_sizes = ('o', 'k', 'h', 'b', 'c', 'z', 'n', 'm', 't', 'q', 's')

31image_sizes = ('o', 'k', 'h', 'b', 'c', 'z', 'n', 'm', 't', 'q', 's')

30

32

31paging = True

33paging = True

34+time_range_support = True

35+time_range_dict = {'day': 60 * 60 * 24,

36+ 'week': 60 * 60 * 24 * 7,

37+ 'month': 60 * 60 * 24 * 7 * 4}

32

38

33

39

34def build_flickr_url(user_id, photo_id):

40def build_flickr_url(user_id, photo_id):

35 return photo_url.format(userid=user_id, photoid=photo_id)

41 return photo_url.format(userid=user_id, photoid=photo_id)

36

42

37

43

38−def request(query, params):

44+def _get_time_range_url(time_range):

39− params['url'] = search_url.format(query=urlencode({'text': query}),

45+ if time_range in time_range_dict:

40− page=params['pageno'])

46+ return time_range_url.format(start=time(), end=str(int(time()) - time_range_dict[time_range]))

47+ return ''

48+

41

49

50+def request(query, params):

51+ params['url'] = (search_url.format(query=urlencode({'text': query}), page=params['pageno'])

52+ + _get_time_range_url(params['time_range']))

42 return params

53 return params

43

54

44

55

searx/engines/youtube_noapi.py+7

@@ -17,10 +17,15 @@ from searx.utils import list_get

17categories = ['videos', 'music']

18paging = True

19language_support = False

20+time_range_support = True

20

21

21# search-url

22# search-url

22base_url = 'https://www.youtube.com/results'

23base_url = 'https://www.youtube.com/results'

23search_url = base_url + '?search_query={query}&page={page}'

24search_url = base_url + '?search_query={query}&page={page}'

25+time_range_url = '&sp=EgII{time_range}%253D%253D'

26+time_range_dict = {'day': 'Ag',

27+ 'week': 'Aw',

28+ 'month': 'BA'}

24

29

25embedded_url = '<iframe width="540" height="304" ' +\

30embedded_url = '<iframe width="540" height="304" ' +\

26 'data-src="//www.youtube-nocookie.com/embed/{videoid}" ' +\

31 'data-src="//www.youtube-nocookie.com/embed/{videoid}" ' +\

@@ -47,6 +52,8 @@ def extract_text_from_dom(result, xpath):

47def request(query, params):

52def request(query, params):

48 params['url'] = search_url.format(query=quote_plus(query),

53 params['url'] = search_url.format(query=quote_plus(query),

49 page=params['pageno'])

54 page=params['pageno'])

55+ if params['time_range'] in time_range_dict:

56+ params['url'] += time_range_url.format(time_range=time_range_dict[params['time_range']])

50

57

51 return params

58 return params

52

59

searx/templates/oscar/preferences.html+2

@@ -158,6 +158,7 @@

158 <th>{{ _("Engine name") }}</th>

159 <th>{{ _("Shortcut") }}</th>

160 <th>{{ _("SafeSearch") }}</th>

161+ <th>{{ _("Time range") }}</th>

161 <th>{{ _("Avg. time") }}</th>

162 <th>{{ _("Avg. time") }}</th>

162 <th>{{ _("Max time") }}</th>

163 <th>{{ _("Max time") }}</th>

163 {% else %}

164 {% else %}

@@ -179,6 +180,7 @@

179 <th>{{ search_engine.name }}</th>

180 <th>{{ search_engine.name }}</th>

180 <td>{{ shortcuts[search_engine.name] }}</td>

181 <td>{{ shortcuts[search_engine.name] }}</td>

181 <td><input type="checkbox" {{ "checked" if search_engine.safesearch==True else ""}} readonly="readonly" disabled="disabled"></td>

182 <td><input type="checkbox" {{ "checked" if search_engine.safesearch==True else ""}} readonly="readonly" disabled="disabled"></td>

183+ <td><input type="checkbox" {{ "checked" if search_engine.time_range_support==True else ""}} readonly="readonly" disabled="disabled"></td>

182 <td class="{{ 'danger' if stats[search_engine.name]['warn_time'] else '' }}">{{ 'N/A' if stats[search_engine.name].time==None else stats[search_engine.name].time }}</td>

184 <td class="{{ 'danger' if stats[search_engine.name]['warn_time'] else '' }}">{{ 'N/A' if stats[search_engine.name].time==None else stats[search_engine.name].time }}</td>

183 <td class="{{ 'danger' if stats[search_engine.name]['warn_timeout'] else '' }}">{{ search_engine.timeout }}</td>

185 <td class="{{ 'danger' if stats[search_engine.name]['warn_timeout'] else '' }}">{{ search_engine.timeout }}</td>

184 {% else %}

186 {% else %}

tests/unit/engines/test_bing_images.py+1

@@ -13,6 +13,7 @@ class TestBingImagesEngine(SearxTestCase):

13 dicto['pageno'] = 1

14 dicto['language'] = 'fr_FR'

15 dicto['safesearch'] = 1

16+ dicto['time_range'] = ''

16 params = bing_images.request(query, dicto)

17 params = bing_images.request(query, dicto)

17 self.assertTrue('url' in params)

18 self.assertTrue('url' in params)

18 self.assertTrue(query in params['url'])

19 self.assertTrue(query in params['url'])

tests/unit/engines/test_bing_news.py+1

@@ -12,6 +12,7 @@ class TestBingNewsEngine(SearxTestCase):

12 dicto = defaultdict(dict)

13 dicto['pageno'] = 1

14 dicto['language'] = 'fr_FR'

15+ dicto['time_range'] = ''

15 params = bing_news.request(query, dicto)

16 params = bing_news.request(query, dicto)

16 self.assertIn('url', params)

17 self.assertIn('url', params)

17 self.assertIn(query, params['url'])

18 self.assertIn(query, params['url'])

tests/unit/engines/test_flickr_noapi.py+1

@@ -15,6 +15,7 @@ class TestFlickrNoapiEngine(SearxTestCase):

15 query = 'test_query'

16 dicto = defaultdict(dict)

17 dicto['pageno'] = 1

18+ dicto['time_range'] = ''

18 params = flickr_noapi.request(query, dicto)

19 params = flickr_noapi.request(query, dicto)

19 self.assertIn('url', params)

20 self.assertIn('url', params)

20 self.assertIn(query, params['url'])

21 self.assertIn(query, params['url'])

tests/unit/engines/test_youtube_noapi.py+1

@@ -11,6 +11,7 @@ class TestYoutubeNoAPIEngine(SearxTestCase):

11 query = 'test_query'

12 dicto = defaultdict(dict)

13 dicto['pageno'] = 0

14+ dicto['time_range'] = ''

14 params = youtube_noapi.request(query, dicto)

15 params = youtube_noapi.request(query, dicto)

15 self.assertIn('url', params)

16 self.assertIn('url', params)

16 self.assertIn(query, params['url'])

17 self.assertIn(query, params['url'])