@@ -26,6 +26,11 @@ paging = False
26URL = 'https://sjp.pwn.pl'
26URL = 'https://sjp.pwn.pl'
27SEARCH_URL = URL + '/szukaj/{query}.html'
27SEARCH_URL = URL + '/szukaj/{query}.html'
29+word_xpath = '//div[@class="query"]'
30+dict_xpath = ['//div[@class="wyniki sjp-so-wyniki sjp-so-anchor"]',
31+ '//div[@class="wyniki sjp-wyniki sjp-anchor"]',
32+ '//div[@class="wyniki sjp-doroszewski-wyniki sjp-doroszewski-anchor"]']
30def request(query, params):
35def request(query, params):
31 params['url'] = SEARCH_URL.format(query=query)
36 params['url'] = SEARCH_URL.format(query=query)
@@ -38,25 +43,30 @@ def response(resp):
39 raise_for_httperror(resp)
44 raise_for_httperror(resp)
40 dom = fromstring(resp.text)
45 dom = fromstring(resp.text)
41− word = extract_text(dom.xpath('//*[@id="content"]/div/div[1]/div/div[1]/div[1]/div[2]/div/div/div[2]/div/div'))
46+ word = extract_text(dom.xpath(word_xpath))
43 definitions = []
48 definitions = []
44− for src in dom.xpath('//*[@id="content"]/div/div[1]/div/div[1]/div[1]/div[2]/div/div/div/div/div/div'):
49+
50+ for dict_src in dict_xpath:
51+ for src in dom.xpath(dict_src):
45− src_text = extract_text(src.xpath('./h1/span[@class="entry-head-title"]/text()')).strip()
52+ src_text = extract_text(src.xpath('.//span[@class="entry-head-title"]/text()')).strip()
47− src_defs = []
54+ src_defs = []
48− for def_item in src.xpath('./div/div[contains(@class, "ribbon-element")]'):
55+ for def_item in src.xpath('.//div[contains(@class, "ribbon-element")]'):
49− if def_item.xpath('./div[@class="znacz"]'):
56+ if def_item.xpath('./div[@class="znacz"]'):
50− sub_defs = []
57+ sub_defs = []
51− for def_sub_item in def_item.xpath('./div[@class="znacz"]'):
58+ for def_sub_item in def_item.xpath('./div[@class="znacz"]'):
52− def_sub_text = extract_text(def_sub_item).lstrip('0123456789. ')
59+ def_sub_text = extract_text(def_sub_item).lstrip('0123456789. ')
53− sub_defs.append(def_sub_text)
60+ sub_defs.append(def_sub_text)
54− src_defs.append((word, sub_defs))
61+ src_defs.append((word, sub_defs))
56− def_text = extract_text(def_item).strip()
63+ def_text = extract_text(def_item).strip()
64+ def_link = def_item.xpath('./span/a/@href')
65+ if 'doroszewski' in def_link[0]:
66+ def_text = f"<a href='{def_link[0]}'>{def_text}</a>"
57− src_defs.append((def_text, ''))
67+ src_defs.append((def_text, ''))
59− definitions.append((src_text, src_defs))
69+ definitions.append((src_text, src_defs))
61 if not definitions:
71 if not definitions:
62 return results
72 return results