Archives/searxng
2
0
Fork 1
mirror of https://github.com/searxng/searxng synced 2024-11-05 06:01:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

Code refactoring.

Browse Source
This commit is contained in:
Plague Doctor 2021-04-16 12:23:27 +10:00
parent 599ff39ddf
commit d275d7a35e
1 changed files with 25 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
searx/engines/sjp.py
View File

@ -26,6 +26,11 @@ paging = False
URL = 'https://sjp.pwn.pl' URL = 'https://sjp.pwn.pl'
SEARCH_URL = URL + '/szukaj/{query}.html' SEARCH_URL = URL + '/szukaj/{query}.html'
word_xpath = '//div[@class="query"]'
dict_xpath = ['//div[@class="wyniki sjp-so-wyniki sjp-so-anchor"]',
'//div[@class="wyniki sjp-wyniki sjp-anchor"]',
'//div[@class="wyniki sjp-doroszewski-wyniki sjp-doroszewski-anchor"]']
def request(query, params): def request(query, params):
params['url'] = SEARCH_URL.format(query=query) params['url'] = SEARCH_URL.format(query=query)
@ -38,14 +43,16 @@ def response(resp):
raise_for_httperror(resp) raise_for_httperror(resp)
dom = fromstring(resp.text) dom = fromstring(resp.text)
word = extract_text(dom.xpath('//*[@id="content"]/div/div[1]/div/div[1]/div[1]/div[2]/div/div/div[2]/div/div')) word = extract_text(dom.xpath(word_xpath))
definitions = [] definitions = []
for src in dom.xpath('//*[@id="content"]/div/div[1]/div/div[1]/div[1]/div[2]/div/div/div/div/div/div'):
src_text = extract_text(src.xpath('./h1/span[@class="entry-head-title"]/text()')).strip() for dict_src in dict_xpath:
for src in dom.xpath(dict_src):
src_text = extract_text(src.xpath('.//span[@class="entry-head-title"]/text()')).strip()
src_defs = [] src_defs = []
for def_item in src.xpath('./div/div[contains(@class, "ribbon-element")]'): for def_item in src.xpath('.//div[contains(@class, "ribbon-element")]'):
if def_item.xpath('./div[@class="znacz"]'): if def_item.xpath('./div[@class="znacz"]'):
sub_defs = [] sub_defs = []
for def_sub_item in def_item.xpath('./div[@class="znacz"]'): for def_sub_item in def_item.xpath('./div[@class="znacz"]'):
@ -54,6 +61,9 @@ def response(resp):
src_defs.append((word, sub_defs)) src_defs.append((word, sub_defs))
else: else:
def_text = extract_text(def_item).strip() def_text = extract_text(def_item).strip()
def_link = def_item.xpath('./span/a/@href')
if 'doroszewski' in def_link[0]:
def_text = f"<a href='{def_link[0]}'>{def_text}</a>"
src_defs.append((def_text, '')) src_defs.append((def_text, ''))
definitions.append((src_text, src_defs)) definitions.append((src_text, src_defs))