@@ -1,48 +1,54 @@
11#!/usr/bin/env python
22
33from urllib import urlencode
4−from json import loads
5−#from urlparse import urljoin
4+#from json import loads
5+from urlparse import urljoin
6+from lxml import html
7+from time import time
68
79categories = ['images']
810
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
11+url = 'https://secure.flickr.com/'
12+search_url = url+'search/?{query}&page={page}'
13+results_xpath = '//div[@class="view display-item-tile"]/figure/div'
1214
1315paging = True
1416
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−
1917
2018def request(query, params):
2119 params['url'] = search_url.format(query=urlencode({'text': query}),
2220 page=params['pageno'])
23− #params['url'] = search_url.format(query=urlencode({'q': query}),
24− # page=params['pageno'])
21+ time_string = str(int(time())-3)
22+ params['cookies']['BX'] = '3oqjr6d9nmpgl&b=3&s=dh'
23+ params['cookies']['xb'] = '421409'
24+ params['cookies']['localization'] = 'en-us'
25+ params['cookies']['flrbp'] = time_string +\
26+ '-3a8cdb85a427a33efda421fbda347b2eaf765a54'
27+ params['cookies']['flrbs'] = time_string +\
28+ '-ed142ae8765ee62c9ec92a9513665e0ee1ba6776'
29+ params['cookies']['flrb'] = '9'
2530 return params
2631
2732
2833def response(resp):
2934 results = []
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'],
35+ dom = html.fromstring(resp.text)
36+ for result in dom.xpath(results_xpath):
37+ img = result.xpath('.//img')
38+
39+ if not img:
40+ continue
41+
42+ img = img[0]
43+ img_src = 'https:'+img.attrib.get('src')
44+
45+ if not img_src:
46+ continue
47+
48+ href = urljoin(url, result.xpath('.//a')[0].attrib.get('href'))
49+ title = img.attrib.get('alt', '')
50+ results.append({'url': href,
51+ 'title': title,
52+ 'img_src': img_src,
3553 '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'})
4854 return results