Spaces:
Sleeping
Sleeping
Update wuzzuf_scraper.py
Browse files- wuzzuf_scraper.py +17 -3
wuzzuf_scraper.py
CHANGED
@@ -29,9 +29,23 @@ def Wuzzuf_scrapping(job_type , job_num):
|
|
29 |
|
30 |
for i in range(int(pages_num) ):
|
31 |
link_new = link1 +'&start='+str(i)
|
32 |
-
|
33 |
-
|
34 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
35 |
|
36 |
# to get the info about jobs
|
37 |
|
|
|
29 |
|
30 |
for i in range(int(pages_num) ):
|
31 |
link_new = link1 +'&start='+str(i)
|
32 |
+
try:
|
33 |
+
data = requests.get(link_new)
|
34 |
+
data.raise_for_status() # Check for HTTP errors
|
35 |
+
soup = BeautifulSoup(data.content, 'html.parser')
|
36 |
+
Title = soup.find_all('h2', {'class': 'css-m604qf'})
|
37 |
+
|
38 |
+
for x in range(len(Title)):
|
39 |
+
title.append(Title[x].find('a').text.strip())
|
40 |
+
loc = soup.find_all('span', {'class': 'css-5wys0k'})[x].text.split(',')
|
41 |
+
location.append(loc[0].strip())
|
42 |
+
country.append(loc[-1].strip())
|
43 |
+
links.append('https://wuzzuf.net' + Title[x].find('a').attrs['href'])
|
44 |
+
|
45 |
+
except requests.exceptions.RequestException as e:
|
46 |
+
# print(f"Request failed: {e}")
|
47 |
+
continue # Skip to the next page if there's an error
|
48 |
+
|
49 |
|
50 |
# to get the info about jobs
|
51 |
|