-
Notifications
You must be signed in to change notification settings - Fork 0
/
script.py
209 lines (164 loc) · 6.31 KB
/
script.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
"""Tribute to AI Saturday Lagos"""
import requests
from bs4 import BeautifulSoup
import datetime
import csv
import argparse
import logging
logging.root.setLevel(logging.INFO)
url = "https://www.linkedin.com/jobs/search/?geoId=105365761&location=Nigeria&sortBy=R&start="
#Creating parser
def get_parser():
"""
parse command line arguments
Returns
-------
parser - ArgumentParser object
"""
parser = argparse.ArgumentParser(description="Linkedin Job Scraper")
parser.add_argument(
"--output_file_name",
type=str,
default="LinkedIn_Jobs.csv",
help="Name of output file",
)
return parser
#creating a function that collects all the jobs url on linkedin
def linkedin (url):
"""
A function that collects all the jobs url on linkedin
Parameters
----------
url: the linkedin jobs homepage
Returns
-------
job_links (list): a list of links to direct jobs on LinkedIn
"""
job_links = []
page_range = [url + str(x) for x in list(range(0, 975, 25))]
for val in page_range:
response = requests.get(val)
soup_object = BeautifulSoup(response.text, "html.parser")
#getting the links in each page
page_links = soup_object.findAll("a")
#print(page_links)
for links in page_links:
href = links.get("href")
if (
href.startswith("https://ng.linkedin.com/jobs/view/")):
job_links.append(href)
return(job_links)
## function to get the contects
def job_content (job_url: list):
"""
Parameters
----------
job_url (list): a list of links to direct jobs on LinkedIn
Returns
------
title, linkedin_link, jd, company, location, date_posted
"""
##testing a link
countss = 0
title = []
linkedin_link = []
jd = []
company = []
location = []
date_posted = []
logging.info("Printing Status code .............")
for val in job_url:
link = val
s = requests.Session()
job = s.get(link)
print(job.status_code)
countss +=1
#print(countss)
if job.status_code == 200: #could also check == requests.codes.ok
job_soup = BeautifulSoup(job.text, "html.parser")
#print(job_soup)
#the job title
job_title = job_soup.find(
"h1", attrs={"class": "top-card-layout__title topcard__title"}
)
#print((job_title))
title.append(job_title.text)
#getting the job description
job_description = job_soup.find(
"div", attrs={"class": "show-more-less-html__markup show-more-less-html__markup--clamp-after-5"}
)
jd.append(job_description.text.lstrip().rstrip())
#company name
company_name = job_soup.find(
"span", attrs={"class": "topcard__flavor"}
)
company.append(company_name.text.strip())
#Location
job_location = job_soup.find(
"span", attrs={"class": "topcard__flavor topcard__flavor--bullet"}
) #topcard__flavor topcard__flavor--bullet
location.append(job_location.text.strip())
#Date Posted
#for jobs posted less than a day
try:
job_date = job_soup.find(
"span", attrs={"class": "posted-time-ago__text posted-time-ago__text--new topcard__flavor--metadata"}
)
ddate = job_date.text.strip()
#for jobs older than a day
except AttributeError:
job_date = job_soup.find(
"span", attrs={"class": "posted-time-ago__text topcard__flavor--metadata"}
)
ddate = job_date.text.strip()
if ( ddate.split(" ")[1] == "day" or\
ddate.split(" ")[1] == "days"):
date_posted.append((datetime.date.today() - datetime.timedelta(days=int(ddate.split(" ")[0]))).isoformat())
elif (ddate.split(" ")[1] == "week" or\
ddate.split(" ")[1] == "weeks"):
date_posted.append((datetime.date.today() - datetime.timedelta(days=int(ddate.split(" ")[0]) * 7)).isoformat())
elif (ddate.split(" ")[1] == "month" or\
ddate.split(" ")[1] == "months"):
date_posted.append((datetime.date.today() - datetime.timedelta(days=int(ddate.split(" ")[0]) * 30)).isoformat())
else:
date_posted.append((datetime.date.today()).isoformat())
#link to post
linkedin_link.append(link)
#title, linkedin_link, jd, company, location, date_posted
else:
continue
print ("Scraping completed")
return title, linkedin_link, jd, company, location, date_posted
#writing the jobs to file
def output(output_file_name: str, job_url: list):
"""
Paramters
---------
output_file_name: the name to be given the the file
job_url: list of links to individual jobs
"""
logging.info("Writing jobs to file...")
title, linkedin_link, jd, company, location, date_posted = job_content (job_url)
with open(output_file_name, "w", newline='', encoding='utf-8') as csv_file:
field_name = ["Title", "Job Description", "Location", "Compnay Name", "Date Posted", "LinkedIn Link"]
writer = csv.writer(csv_file)
writer.writerow(field_name)
for a,b,c,d,e,f in zip(title, jd, location, company, date_posted, linkedin_link):
writer.writerow([a,b,c,d,e,f])
job_num = len(title)
logging.info(f"Successfully wrote story number {job_num}")
logging.info(
f"Scraping done. A total of {job_num} Jobs were scraped!")
if __name__ == "__main__":
logging.info("--------------------------------------")
logging.info("Starting scraping...")
logging.info("--------------------------------------")
# initialize parser
parser = get_parser()
params, unknown = parser.parse_known_args()
scraped_links = linkedin(url)
output(params.output_file_name, scraped_links)
""" Author: Abraham Owodunni
Email: [email protected]
Twitter: @AbrahamOwos
"""