|
@@ -1,37 +1,48 @@
|
1
|
1
|
#!/usr/bin/env python
|
2
|
2
|
|
3
|
3
|
from urllib import urlencode
|
4
|
|
-from lxml import html
|
5
|
|
-from urlparse import urljoin
|
|
4
|
+from json import loads
|
|
5
|
+#from urlparse import urljoin
|
6
|
6
|
|
7
|
7
|
categories = ['images']
|
8
|
8
|
|
9
|
|
-url = 'https://secure.flickr.com/'
|
10
|
|
-search_url = url+'search/?{query}&page={page}'
|
11
|
|
-results_xpath = '//div[@id="thumbnails"]//a[@class="rapidnofollow photo-click" and @data-track="photo-click"]' # noqa
|
|
9
|
+# url = 'https://secure.flickr.com/'
|
|
10
|
+# search_url = url+'search/?{query}&page={page}'
|
|
11
|
+# results_xpath = '//div[@id="thumbnails"]//a[@class="rapidnofollow photo-click" and @data-track="photo-click"]' # noqa
|
12
|
12
|
|
13
|
13
|
paging = True
|
14
|
14
|
|
|
15
|
+# text=[query]
|
|
16
|
+# TODO clean "extras"
|
|
17
|
+search_url = 'https://api.flickr.com/services/rest?extras=can_addmeta%2Ccan_comment%2Ccan_download%2Ccan_share%2Ccontact%2Ccount_comments%2Ccount_faves%2Ccount_notes%2Cdate_taken%2Cdate_upload%2Cdescription%2Cicon_urls_deep%2Cisfavorite%2Cispro%2Clicense%2Cmedia%2Cneeds_interstitial%2Cowner_name%2Cowner_datecreate%2Cpath_alias%2Crealname%2Csafety_level%2Csecret_k%2Csecret_h%2Curl_c%2Curl_h%2Curl_k%2Curl_l%2Curl_m%2Curl_n%2Curl_o%2Curl_q%2Curl_s%2Curl_sq%2Curl_t%2Curl_z%2Cvisibility&per_page=50&page={page}&{query}&sort=relevance&method=flickr.photos.search&api_key=ad11b34c341305471e3c410a02e671d0&format=json' # noqa
|
|
18
|
+
|
15
|
19
|
|
16
|
20
|
def request(query, params):
|
17
|
|
- params['url'] = search_url.format(query=urlencode({'q': query}),
|
|
21
|
+ params['url'] = search_url.format(query=urlencode({'text': query}),
|
18
|
22
|
page=params['pageno'])
|
|
23
|
+ #params['url'] = search_url.format(query=urlencode({'q': query}),
|
|
24
|
+ # page=params['pageno'])
|
19
|
25
|
return params
|
20
|
26
|
|
21
|
27
|
|
22
|
28
|
def response(resp):
|
23
|
|
- global base_url
|
24
|
29
|
results = []
|
25
|
|
- dom = html.fromstring(resp.text)
|
26
|
|
- for result in dom.xpath(results_xpath):
|
27
|
|
- href = urljoin(url, result.attrib.get('href'))
|
28
|
|
- img = result.xpath('.//img')[0]
|
29
|
|
- title = img.attrib.get('alt', '')
|
30
|
|
- img_src = img.attrib.get('data-defer-src')
|
31
|
|
- if not img_src:
|
32
|
|
- continue
|
33
|
|
- results.append({'url': href,
|
34
|
|
- 'title': title,
|
35
|
|
- 'img_src': img_src,
|
|
30
|
+ images = loads(resp.text[14:-1])["photos"]["photo"]
|
|
31
|
+ for i in images:
|
|
32
|
+ results.append({'url': i['url_s'],
|
|
33
|
+ 'title': i['title'],
|
|
34
|
+ 'img_src': i['url_s'],
|
36
|
35
|
'template': 'images.html'})
|
|
36
|
+ #dom = html.fromstring(resp.text)
|
|
37
|
+ #for result in dom.xpath(results_xpath):
|
|
38
|
+ # href = urljoin(url, result.attrib.get('href'))
|
|
39
|
+ # img = result.xpath('.//img')[0]
|
|
40
|
+ # title = img.attrib.get('alt', '')
|
|
41
|
+ # img_src = img.attrib.get('data-defer-src')
|
|
42
|
+ # if not img_src:
|
|
43
|
+ # continue
|
|
44
|
+ # results.append({'url': href,
|
|
45
|
+ # 'title': title,
|
|
46
|
+ # 'img_src': img_src,
|
|
47
|
+ # 'template': 'images.html'})
|
37
|
48
|
return results
|