adpro commited on
Commit
07df736
·
verified ·
1 Parent(s): c4762ea

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +32 -4
app.py CHANGED
@@ -9,11 +9,39 @@ from urllib.parse import parse_qs
9
 
10
  def run_lora(prompt,site,start,end):
11
 
12
- j = search("inurl:"+site +"+"+ prompt + "&tbs=cdr%3A1%2Ccd_min%3A"+start+"%2Ccd_max%3A" + end)
13
  links=""
14
- for i in j:
15
- print(i)
16
- links+=str(i)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
 
18
  with gr.Blocks() as app:
19
  gr.HTML("""<html>
 
9
 
10
  def run_lora(prompt,site,start,end):
11
 
12
+ j = "inurl:"+site +"+"+ prompt + "&tbs=cdr%3A1%2Ccd_min%3A"+start+"%2Ccd_max%3A" + end,proxy="https://proxyhere.net:port")
13
  links=""
14
+
15
+ page = requests.get(j, headers = {'User-agent': 'your bot 0.1'})
16
+ soup = BeautifulSoup(page.content,"html.parser")
17
+ mj = extract_results(soup)
18
+ print(mj)
19
+ def extract_results(soup):
20
+ main = soup.select_one("#main")
21
+
22
+ res = []
23
+ for gdiv in main.select('.g, .fP1Qef'):
24
+ res.append(extract_section(gdiv))
25
+ return res
26
+
27
+ def extract_section(gdiv):
28
+ # Getting our elements
29
+ title = gdiv.select_one('h3')
30
+ link = gdiv.select_one('a')
31
+ description = gdiv.find('.BNeawe')
32
+ return {
33
+ # Extract title's text only if text is found
34
+ 'title': title.text if title else None,
35
+
36
+ 'link': link['href'] if link else None,
37
+ 'description': description.text if description else None
38
+ }
39
+ def extract_href(href):
40
+ url = urlparse(href)
41
+ query = parse_qs(url.query)
42
+ if not ('q' in query and query['q'] and len(query['q']) > 0):
43
+ return None
44
+ return query['q'][0]
45
 
46
  with gr.Blocks() as app:
47
  gr.HTML("""<html>