Skip to content

Commit 9eaf431

Browse files
committed
wisdom job
1 parent d0830f7 commit 9eaf431

File tree

1 file changed

+61
-0
lines changed

1 file changed

+61
-0
lines changed

Diff for: WisdomJobs.py

+61
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,61 @@
1+
import requests
2+
from bs4 import BeautifulSoup
3+
import json
4+
import datetime
5+
import os
6+
import re
7+
import pprint
8+
pp = pprint.PrettyPrinter(indent=4)
9+
10+
11+
class Wisdom:
12+
def __init__(self,url):
13+
self.url=url
14+
self.primaryurl="https://www.wisdomjobs.com/"
15+
16+
def ParsePage(self,url):
17+
try:
18+
res = requests.get(url)
19+
soup = BeautifulSoup(res.content,'lxml')
20+
return soup
21+
except Exception as ex:
22+
return None
23+
24+
def GetAllJobs(self,content):
25+
jobscontainer = content.findAll('div', {'class': 'jobDiv'})
26+
jobslink=[os.path.join(self.primaryurl,j.a['href']) for j in jobscontainer if(j.find('a'))]
27+
return jobslink
28+
29+
def Run(self):
30+
jobslinks=self.GetAllJobs(self.ParsePage(self.url))
31+
for j in jobslinks:
32+
content=self.ParsePage(j)
33+
Cont=content.findAll('table')
34+
data=self.ParseSinglePage(Cont)
35+
pp.pprint(data)
36+
37+
def ParseSinglePage(self,Cont):
38+
try:
39+
for t in Cont:
40+
venue=[list(tds.stripped_strings) for tds in t.findAll("span",attrs={'class': 'text-muted'})]
41+
if (len(venue)==2) and int(re.findall(r'[\d]*',venue[-1][-1])[7])<20:
42+
Li=t("li")
43+
datas=[l.text for l in Li]
44+
jobs={}
45+
if len(datas)!=0:
46+
if "Walkin" in datas[0]:
47+
jobrole=datas[0].split("-")[1:]
48+
full=" ".join(jobrole).split("|")[0].split("walk in for")
49+
jobs['title']=full[-1]
50+
jobs['company']=full[0]
51+
jobs['exeprince']=datas[1]
52+
jobs['city']=datas[2]
53+
jobs['walkindate']=datas[3]+""+datas[4]
54+
return jobs
55+
except:
56+
return None
57+
58+
url='https://www.wisdomjobs.com/latest-walkins'
59+
w1=Wisdom(url)
60+
w1.Run()
61+

0 commit comments

Comments
 (0)