def run(url):
soup = get_javascript_soup_delayed(url, 'current-openings-item')
jobs_list = soup.find_all('div', {'class':'current-openings-details'})
for job_entry in jobs_list:
globals.job_title = job_entry.find('span', {'class':'current-opening-title'}).text.strip()
if job_entry.find('span', {'class':'current-opening-location-item'}):
globals.job_location = job_entry.find('span', {'class':'current-opening-location-item'}).text.strip()
# Calculate post date relative to current date and store it
posted_ago = job_entry.find('span', {'class':'current-opening-post-date'}).text.split(' ')
if posted_ago[0] == 'a':
globals.job_post_date = date_ago(1, posted_ago[1])
elif posted_ago[0].lower() == 'yesterday':
globals.job_post_date = date_ago(1, 'day')
elif posted_ago[0] == '30+':
# over 30 days ago
globals.job_post_date = date_ago(31, posted_ago[1])
else:
globals.job_post_date = date_ago(int(posted_ago[0]), posted_ago[1])
if job_entry.find('span', {'class':'current-opening-worker-catergory'}):
globals.full_or_part = job_entry.find('span', {'class':'current-opening-worker-catergory'}).text.strip()
globals.info_link = 'https://workforcenow.adp.com/mascsr/default/mdf/recruitment/recruitment.html?cid=b4842dc2-cd32-4f0f-88d3-b259fbc96f09&ccId=19000101_000001&type=MP&lang'
globals.job_summary = globals.info_link
update_db(organization)
reset_vars()
def run(url):
soup = get_javascript_soup(url)
jobs_list = soup.select('div.wpb_wrapper > p > a')
for job_entry in jobs_list:
globals.job_title = job_entry.text.strip()
globals.info_link = job_entry['href']
update_db(organization)
def run(url):
soup = get_soup(url)
jobs_list = soup.find_all('h4')
for job_entry in jobs_list:
globals.job_title = job_entry.a.text
globals.info_link = job_entry.a['href']
globals.job_summary = globals.info_link
listing_soup = get_soup(globals.info_link)
if listing_soup.body.find_all('p', string="Job Type: Full-time"):
globals.full_or_part = 'Full-time'
elif listing_soup.body.find_all('p', string="Job Type: Part-time"):
globals.full_or_part = 'Part-time'
date_text = listing_soup.body.find_all(
'span', {'class': 'subtitle'})[0].text.split()
month_string = date_text[2]
day = int(date_text[3][0:len(date_text[3]) - 1])
year = int(date_text[4])
month = month_to_num(month_string)
globals.job_post_date = datetime(year, month, day)
update_db(organization)
def run(url):
soup = get_javascript_soup(url)
jobs_list = soup.select('div.entry-content div.small-12.columns > p > a')
for job_entry in jobs_list:
globals.job_title = job_entry.text
globals.info_link = job_entry['href']
update_db(organization)
def run(url):
soup = get_soup("https://www.211la.org/careers")
jobs_list = soup.find_all("div", {"class": "jobBtn"})
for job_entry in jobs_list:
for child in job_entry.find_all("a"):
globals.job_title = child.text
globals.info_link = child.get('href')
update_db(organization)
def run(url):
soup = get_soup(url)
jobs_div = soup.find('div', {'class':'sqs-block-content'})
jobs_list = jobs_div.find_all('p')
for job_entry in jobs_list[4:len(jobs_list)-3]:
globals.job_title = job_entry.a.text.strip()
globals.info_link = 'https://lafh.org' + job_entry.a['href']
update_db(organization)
def run(url):
soup = get_javascript_soup(url)
jobs_list = soup.find('table',{'class':'srJobList'}).tbody.find_all('tr')[1:]
for job_entry in jobs_list:
globals.job_title = job_entry.find('td',{'class':'srJobListJobTitle'}).text.strip()
onClickLink = job_entry['onclick']
globals.info_link = onClickLink[13:len(onClickLink)-3]
globals.full_or_part = job_entry.find('td',{'class':'srJobListTypeOfEmployment'}).text
globals.job_location = clean_location(job_entry.find('td',{'class':'srJobListLocation'}).text)
globals.job_zip_code = city_to_zip(globals.job_location)
update_db(organization)
def run(url):
soup = get_soup(url)
jobs_list = soup.select('div[class*="JobGrid-"]')[0]
for job_entry in jobs_list.find_all('a'):
globals.info_link = 'https://path.catsone.com' + job_entry['href']
job_row = job_entry.find('div', {'class':'row'})
job_divs = job_row.find_all('div')
globals.job_title = job_divs[0].text.strip()
globals.job_location = clean_location(job_divs[2].text.strip())
globals.job_zip_code = city_to_zip(globals.job_location)
update_db(organization)
def run(url):
soup = get_soup(url)
jobs_list = soup.find('ul', {'class': 'lcp_catlist'})
for job_entry in jobs_list.find_all('li'):
globals.job_title = job_entry.a.text.strip()
globals.info_link = job_entry.a['href']
job_soup = get_soup(globals.info_link)
summary_match = job_soup.find(text=re.compile("Position Purpose:"))
if summary_match is not None:
globals.job_summary = summary_match.parent.parent.text
else:
raise globals.ParseError(globals.info_link,
'Cannot find job summary')
update_db(organization)
def run(url):
globals.job_post_date = ''
next_page_url = url
soup = get_javascript_soup_delayed(next_page_url, 'job-table-title')
while soup:
job_table = soup.find('tbody')
for job_row in job_table.find_all('tr'):
globals.job_title = job_row.find('td', {
'class': 'job-table-title'
}).a.text.strip()
globals.info_link = 'https://www.governmentjobs.com' + job_row.find(
'td', {
'class': 'job-table-title'
}).a['href']
globals.salary = job_row.find('td', {
'class': 'job-table-salary'
}).text
globals.full_or_part = job_row.find('td', {
'class': 'job-table-type'
}).text
# Get soup for job listing to get more info
job_soup = get_soup(globals.info_link)
info_container = job_soup.find('div',
{'class': 'summary container'})
globals.job_location = clean_location(
info_container.find('div', {
'id': 'location-label-id'
}).parent.find_all('div')[2].text)
globals.job_zip_code = city_to_zip(globals.job_location)
globals.job_summary = job_soup.find('div', {
'id': 'details-info'
}).find('p').text
update_db(organization)
reset_vars()
if not 'disabled' in soup.find('li', {
'class': 'PagedList-skipToNext'
}).get("class"):
next_page_url = 'https://www.governmentjobs.com/careers/lahsa?' + soup.find(
'li', {
'class': 'PagedList-skipToNext'
}).a['href'].split('?')[1]
soup = get_javascript_soup_delayed(next_page_url,
'job-table-title')
else:
soup = False
def run(url):
globals.job_post_date = ''
soup = get_soup(url)
jobs_table = soup.find('table',{'id':'job-result-table'})
for job_row in jobs_table.find_all('tr',{'class':'job-result'}):
job_title_cell = job_row.find('td',{'class':'job-result-title-cell'})
globals.job_title = job_title_cell.a.text.strip()
globals.info_link = 'https://pennylanecenters.jobs.net' + job_title_cell.a['href']
globals.job_summary = globals.info_link
globals.job_location = clean_location(job_row.find('div',{'class':'job-location-line'}).text)
globals.job_zip_code = city_to_zip(globals.job_location)
# Get Job Soup
job_soup = get_soup(globals.info_link)
globals.full_or_part = job_soup.find('li',{'class':'job-employee-type'}).find('div',{'class':'secondary-text-color'}).text
globals.job_post_date = string_to_date(job_soup.find('li',{'class':'job-date-posted'}).find('div',{'class':'secondary-text-color'}).text)
update_db(organization)
reset_vars()
def run(url):
soup = get_soup(url)
article = soup.find('article')
jobs_list = article.find_all('p')
for job_entry in jobs_list:
if 'Posted ' in job_entry.text:
job_element = job_entry.find('a')
globals.job_title = job_element.text
globals.info_link = job_element['href']
globals.job_summary = globals.info_link
date = job_entry.text.split('Posted ')[1].split('/')
month = int(date[0])
day = int(date[1])
year = int(date[2])
globals.job_post_date = datetime(year, month, day)
update_db(organization)
reset_vars()
def run(url):
soup = get_javascript_soup(url)
job_listings = soup.find_all('div',{'class':'job-listing-job-item'})
for job_listing in job_listings:
job_description = job_listing.find_all('span')
# Get job title and link
globals.job_title = job_description[0].a.text
globals.info_link = 'https://recruiting.paylocity.com' + job_description[0].a['href']
globals.job_summary = globals.info_link
# Get date as string
date = job_description[1].text
# Clean up date string by removing trailing -'s, then split and convert to datetime object
if date[len(date)-2] == '-':
date = date[0:len(date)-3]
date = date.strip().split('/')
month = int(date[0])
day = int(date[1])
year = int(date[2])
globals.job_post_date = datetime(year, month, day)
# Get Location
globals.job_location = job_listing.find('div',{'class':'location-column'}).span.text
# Get soup of job listing to scrape more info
listing_soup = get_soup(globals.info_link)
listing_body = listing_soup.find('body').find_all('p')
# Retrieve Full/Part-time and Salary info if available
if 'Location' in listing_body[0].text:
location_string = listing_body[0].text.split(':')[1].lstrip()
zip_code_result = re.search(r'(\d{5})', location_string)
if zip_code_result != None:
globals.job_zip_code = zip_code_result.group(1)
# can't get city since there's no standard. It could be
# "Hollywood", "Koreatown, Los angeles, California", or even
# "Multiple Locations"
if len(globals.job_zip_code) == 0:
globals.job_zip_code = globals.city_to_zip(globals.job_location)
if 'Status' in listing_body[1].text:
globals.full_or_part = listing_body[1].text[8:]
if 'Salary' in listing_body[2].text:
globals.salary = listing_body[2].text[14:]
update_db(organization)