Spaces:
Sleeping
Sleeping
Update wuzzuf_scraper.py
Browse files- wuzzuf_scraper.py +4 -3
wuzzuf_scraper.py
CHANGED
@@ -3,10 +3,11 @@ import pandas as pd
|
|
3 |
from bs4 import BeautifulSoup
|
4 |
import numpy as np
|
5 |
import re
|
6 |
-
from selenium import
|
|
|
7 |
|
8 |
# wuzzuf function
|
9 |
-
def Wuzzuf_scrapping(job_type , job_num):
|
10 |
job1 = job_type.split(" ")[0]
|
11 |
job2 = job_type.split(" ")[1]
|
12 |
link1 = 'https://wuzzuf.net/search/jobs/?a=navbl&q='+job1+'%20'+job1
|
@@ -112,7 +113,7 @@ def Wuzzuf_scrapping(job_type , job_num):
|
|
112 |
|
113 |
|
114 |
# get Job_Categories , Skills_And_Tools , job_description , and job_requirements from urls
|
115 |
-
driver = webdriver.Chrome('chromedriver',options=options)
|
116 |
#driver.implicitly_wait(10)
|
117 |
driver.get(links[x])
|
118 |
Job_Categories.append(driver.find_element(By.XPATH ,'//*[@id="app"]/div/main/section[2]/div[5]').text.split("\n")[1:])
|
|
|
3 |
from bs4 import BeautifulSoup
|
4 |
import numpy as np
|
5 |
import re
|
6 |
+
from selenium.webdriver.common.by import By
|
7 |
+
|
8 |
|
9 |
# wuzzuf function
|
10 |
+
def Wuzzuf_scrapping(job_type , job_num,driver):
|
11 |
job1 = job_type.split(" ")[0]
|
12 |
job2 = job_type.split(" ")[1]
|
13 |
link1 = 'https://wuzzuf.net/search/jobs/?a=navbl&q='+job1+'%20'+job1
|
|
|
113 |
|
114 |
|
115 |
# get Job_Categories , Skills_And_Tools , job_description , and job_requirements from urls
|
116 |
+
#driver = webdriver.Chrome('chromedriver',options=options)
|
117 |
#driver.implicitly_wait(10)
|
118 |
driver.get(links[x])
|
119 |
Job_Categories.append(driver.find_element(By.XPATH ,'//*[@id="app"]/div/main/section[2]/div[5]').text.split("\n")[1:])
|