sagunsh · March 8, 2025 02:47
diff --git a/seek_monitoring.py b/seek_monitoring.py
 # author: sagunsh
 # description: monitor jobs on seek.com.au
 # requires: python 3.6+
 #
 # Usage
 # help: python seek_monitoring.py --help
 # print to console: python seek_monitoring.py --keyword="software engineer"
 # save to csv (50 jobs): python seek_monitoring.py --keyword="software engineer" --max=50 --csv
 # todo: send email

 import argparse
 import json
 import csv
 import urllib.parse
 import urllib.request


 BASE_URL = 'https://www.seek.com.au/'
 SEARCH_PATH = '/api/jobsearch/v5/search'


 def get_response(url, max_retries=10):
    retry = 0
    headers = {
        'accept': 'application/json, text/plain, */*',
        'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/133.0.0.0 Safari/537.36',
    }

    while retry < max_retries:
        try:
            req = urllib.request.Request(url, headers=headers)
            with urllib.request.urlopen(req, timeout=30) as response:
                return response.read().decode()
        except:
            pass

        retry += 1


 def search_jobs(keyword, max_count):
    if not isinstance(keyword, str) or len(keyword) == 0:
        return []

    if not isinstance(max_count, int) or max_count <= 0 or max_count > 100:
        max_count = 25

    params = {
        'page': '1',
        'keywords': keyword,
        'pageSize': max_count,
        'sortmode': 'KeywordRelevance',  # or 'ListedDate'
    }
    search_url = urllib.parse.urljoin(BASE_URL, SEARCH_PATH + '?' + urllib.parse.urlencode(params))

    try:
        response = get_response(search_url)
        jobs = json.loads(response).get('data', [])
    except:
        jobs = []

    results = []
    for job in jobs:
        job_dict = {
            'title': job.get('title'),
            'url': 'https://www.seek.com.au/job/' + job.get('id'),
            'company': job.get('advertiser').get('description'),
            'posted_on': job.get('listingDate').split('T')[0],
            'salary': job.get('salaryLabel'),
        }
        results.append(job_dict)

    return results


 def generate_html_table(data):
    if len(data) == 0:
        return '<p>No data available</p>'

    headers = data[0].keys()
    html = '<table border="1" cellspacing="0" cellpadding="5" style="border-collapse: collapse;">'
    html += '<tr>'
    for header in headers:
        if header != 'url':
            html += f'<th style="background-color: #f2f2f2; padding: 8px; text-align: left;">{header.title()}</th>'
    html += '</tr>'

    for row in data:
        html += '<tr>'
        for key in headers:
            if key == 'title':
                html += f'<td style="padding: 8px;"><a href="{row["url"]}" target="_blank">{row[key]}</a></td>'
            elif key == 'url':
                continue
            else:
                html += f'<td style="padding: 8px;">{row[key]}</td>'
        html += '</tr>'
    html += '</table>'
    return html


 def save_to_csv(data):
    if len(data) == 0:
        return False

    file_name = f'seek_jobs.csv'
    with open(file_name, 'w') as csvfile:
        writer = csv.DictWriter(csvfile, fieldnames=jobs[0].keys())
        writer.writeheader()
        writer.writerows(jobs)

    return file_name


 if __name__ == '__main__':
    parser = argparse.ArgumentParser(description='Monitor seek jobs')
    parser.add_argument('--keyword', help='Search keyword', default='python developer')
    parser.add_argument('--max', help='Max number of jobs', default=25, type=int)
    parser.add_argument('--csv', help='Save output to CSV file', action='store_true')
    parser.add_argument('--email', help='Send email', action='store_true')
    args = parser.parse_args()

    print(f'searching for {args.keyword} jobs')
    jobs = search_jobs(keyword=args.keyword, max_count=args.max)

    if args.csv:
        file_name = save_to_csv(jobs)
        if file_name:
            print(f'Saved to {file_name}')
        else:
            print('No data available')

    if args.email:
        html_table = generate_html_table(jobs)
        html = f'<html lang="en"><body style="font-family:Tahoma">{html_table}</body></html>'
        print(html)

        print('\n\nTodo: Send email to myself')

    if not args.csv and not args.email:
        for job in jobs:
            print(job)
	# author: sagunsh
	# description: monitor jobs on seek.com.au
	# requires: python 3.6+
	#
	# Usage
	# help: python seek_monitoring.py --help
	# print to console: python seek_monitoring.py --keyword="software engineer"
	# save to csv (50 jobs): python seek_monitoring.py --keyword="software engineer" --max=50 --csv
	# todo: send email

	import argparse
	import json
	import csv
	import urllib.parse
	import urllib.request


	BASE_URL = 'https://www.seek.com.au/'
	SEARCH_PATH = '/api/jobsearch/v5/search'


	def get_response(url, max_retries=10):
	retry = 0
	headers = {
	'accept': 'application/json, text/plain, /',
	'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/133.0.0.0 Safari/537.36',
	}

	while retry < max_retries:
	try:
	req = urllib.request.Request(url, headers=headers)
	with urllib.request.urlopen(req, timeout=30) as response:
	return response.read().decode()
	except:
	pass

	retry += 1


	def search_jobs(keyword, max_count):
	if not isinstance(keyword, str) or len(keyword) == 0:
	return []

	if not isinstance(max_count, int) or max_count <= 0 or max_count > 100:
	max_count = 25

	params = {
	'page': '1',
	'keywords': keyword,
	'pageSize': max_count,
	'sortmode': 'KeywordRelevance', # or 'ListedDate'
	}
	search_url = urllib.parse.urljoin(BASE_URL, SEARCH_PATH + '?' + urllib.parse.urlencode(params))

	try:
	response = get_response(search_url)
	jobs = json.loads(response).get('data', [])
	except:
	jobs = []

	results = []
	for job in jobs:
	job_dict = {
	'title': job.get('title'),
	'url': 'https://www.seek.com.au/job/' + job.get('id'),
	'company': job.get('advertiser').get('description'),
	'posted_on': job.get('listingDate').split('T')[0],
	'salary': job.get('salaryLabel'),
	}
	results.append(job_dict)

	return results


	def generate_html_table(data):
	if len(data) == 0:
	return '<p>No data available</p>'

	headers = data[0].keys()
	html = '<table border="1" cellspacing="0" cellpadding="5" style="border-collapse: collapse;">'
	html += '<tr>'
	for header in headers:
	if header != 'url':
	html += f'<th style="background-color: #f2f2f2; padding: 8px; text-align: left;">{header.title()}</th>'
	html += '</tr>'

	for row in data:
	html += '<tr>'
	for key in headers:
	if key == 'title':
	html += f'<td style="padding: 8px;"><a href="{row["url"]}" target="_blank">{row[key]}</a></td>'
	elif key == 'url':
	continue
	else:
	html += f'<td style="padding: 8px;">{row[key]}</td>'
	html += '</tr>'
	html += '</table>'
	return html


	def save_to_csv(data):
	if len(data) == 0:
	return False

	file_name = f'seek_jobs.csv'
	with open(file_name, 'w') as csvfile:
	writer = csv.DictWriter(csvfile, fieldnames=jobs[0].keys())
	writer.writeheader()
	writer.writerows(jobs)

	return file_name


	if __name__ == '__main__':
	parser = argparse.ArgumentParser(description='Monitor seek jobs')
	parser.add_argument('--keyword', help='Search keyword', default='python developer')
	parser.add_argument('--max', help='Max number of jobs', default=25, type=int)
	parser.add_argument('--csv', help='Save output to CSV file', action='store_true')
	parser.add_argument('--email', help='Send email', action='store_true')
	args = parser.parse_args()

	print(f'searching for {args.keyword} jobs')
	jobs = search_jobs(keyword=args.keyword, max_count=args.max)

	if args.csv:
	file_name = save_to_csv(jobs)
	if file_name:
	print(f'Saved to {file_name}')
	else:
	print('No data available')

	if args.email:
	html_table = generate_html_table(jobs)
	html = f'<html lang="en"><body style="font-family:Tahoma">{html_table}</body></html>'
	print(html)

	print('\n\nTodo: Send email to myself')

	if not args.csv and not args.email:
	for job in jobs:
	print(job)