def run(url):
soup = get_javascript_soup(url)
job_listings = soup.find_all('div', {'class': 'job-listing-job-item'})
job_class = Job(organization, "")
job_class.organization_id = organization_id
insert_count = 0
for job_listing in job_listings:
job_class.title = job_listing.find('span', {
'class': 'job-item-title'
}).a.text.strip()
job_class.info_link = 'https://recruiting.paylocity.com' + \
job_listing.find('span', {'class': 'job-item-title'}).a['href']
details = get_soup(job_class.info_link)
location = details.find('div', {'class': 'preview-location'})
if location.a:
job_class.location = location.a.text
zipcode = location.a['href'].split('+')[-1]
try:
job_class.zip_code = int(zipcode)
except ValueError:
# generate a zip code if one is not available
job_class.zip_code = city_to_zip(job_class.location)
else:
job_class.location = ''
job_class.zip_code = ''
job_class.post_date = string_to_date(
job_listing.find('div', {
'class': 'job-title-column'
}).find_all('span')[1].text.split(' - ')[0])
insert_count += job_insert(job_class)
return insert_count
def run(url):
soup = get_soup(url)
jobs_list = soup.select('div[class*="JobGrid-"]')[0]
job_class= Job(organization, "")
job_class.organization_id= organization_id
insert_count= 0
for job_entry in jobs_list.find_all('a'):
job_class.info_link = 'https://path.catsone.com' + job_entry['href']
job_row = job_entry.find('div', {'class': 'row'})
job_divs = job_row.find_all('div')
job_class.title = job_divs[0].text.strip()
job_class.location = clean_location(job_divs[2].text.strip())
job_class.zip_code = city_to_zip(job_class.location)
insert_count+= job_insert(job_class)
# Possible to get more info by scraping each job link, but the listings are extremely poorly written/standardized; scraper below works for most of the listings, but a few poorly written listings break the scraper
# job_soup = get_soup(info_link)
# job_description = job_soup.find('div',{'class':'Job__StyledDescription-s1h17u0t-0'})
# if '\n' in job_description.find_all('strong')[0].text:
# full_or_part = job_description.find_all('strong')[0].text.split('\n')[1].strip()
# salary = job_description.find_all('strong')[0].text.split('\n')[2].strip().split(': ')[1]
# else:
# full_or_part = job_description.find_all('strong')[1].text.strip()
# salary = job_description.find_all('strong')[2].text.split('\n')[0].split(':')[1].strip()
return insert_count
def run(url):
soup = get_javascript_soup_delayed_and_click(url, 'hrmSearchButton')
job_listings = soup.find_all('tr', {'class': 'ReqRowClick'})
job_class = Job(organization, "")
job_class.organization_id = organization_id
insert_count = 0
for job_row in job_listings:
job_class.title = job_row.find('td', {
'class': 'posTitle'
}).text.strip()
job_class.info_link = 'http://mhala.hrmdirect.com/employment/' + \
job_row.find('td', {'class': 'posTitle'}).a['href']
job_class.location = job_row.find('td', {'class': 'cities'}).text
job_class.zip_code = globals.city_to_zip(job_class.location)
job_soup = get_soup(job_class.info_link)
summary = job_soup.find(string=["Summary:", "Summary: "])
if summary:
summary_parent = summary.parent
summary_parent.clear()
job_class.summary = summary_parent.find_parent("p").text.strip()
else:
job_class.summary = ''
insert_count += job_insert(job_class)
return insert_count
def run(url):
soup = get_javascript_soup(url)
jobs_list = soup.find(
'table', {'class': 'srJobList'}).tbody.find_all('tr')[1:]
job_class= Job(organization, "")
job_class.organization_id= organization_id
insert_count= 0
for job_entry in jobs_list:
job_class.title = job_entry.find(
'td', {'class': 'srJobListJobTitle'}).text.strip()
onClickLink = job_entry['onclick']
job_class.info_link = onClickLink[13:len(onClickLink) - 3]
job_class.full_or_part = job_entry.find(
'td', {'class': 'srJobListTypeOfEmployment'}).text
job_class.location = job_entry.find(
'td', {'class': 'srJobListLocation'}).text
location_parts = job_class.location.split(',')
if len(location_parts) > 1 and len(
location_parts[-1]) and location_parts[-1].strip().lower() != 'ca':
# skip job if state is not CA
print('Skip location: %s' % job_class.location)
continue
job_class.zip_code = city_to_zip(location_parts[0])
insert_count+= job_insert(job_class)
return insert_count
def run(url):
soup = get_soup(url)
jobs_table = soup.find('table', {'id': 'job-result-table'})
job_class = Job(organization, "")
job_class.post_date = ""
job_class.organization_id = organization_id
insert_count = 0
for job_row in jobs_table.find_all('tr', {'class': 'job-result'}):
job_title_cell = job_row.find('td', {'class': 'job-result-title-cell'})
job_class.title = job_title_cell.a.text.strip()
job_class.info_link = 'https://pennylanecenters.jobs.net' + \
job_title_cell.a['href']
job_class.location = clean_location(
job_row.find('div', {
'class': 'job-location-line'
}).text)
job_class.zip_code = city_to_zip(job_class.location)
# Get Job Soup
job_soup = get_soup(job_class.info_link)
job_class.full_or_part = job_soup.find('li', {
'class': 'job-employee-type'
}).find('div', {
'class': 'secondary-text-color'
}).text
job_class.post_date = string_to_date(
job_soup.find('li', {
'class': 'job-date-posted'
}).find('div', {
'class': 'secondary-text-color'
}).text)
insert_count += job_insert(job_class)
return insert_count
def run(url):
soup = get_soup(url)
jobs_list = soup.find_all('div', {'class': 'list-data'})
job_class = Job(organization, "")
job_class.organization_id = organization_id
insert_count = 0
for job_entry in jobs_list:
job_info = job_entry.find('div', {'class': 'job-info'})
job_class.title = job_info.find('span', {
'class': 'job-title'
}).text.strip()
job_class.info_link = job_info.h4.a['href']
job_class.full_or_part = job_entry.find('div', {
'class': 'job-type'
}).text.strip()
job_class.location = clean_location(
job_entry.find('div', {
'class': 'job-location'
}).text.strip())
job_class.zip_code = city_to_zip(job_class.location)
relative_date = job_entry.find('div', {
'class': 'job-date'
}).text.strip().split(' ')
job_class.post_date = date_ago(int(relative_date[1]), relative_date[2])
job_class.summary = job_entry.find('div', {
'class': 'job-description'
}).p.text.strip()
insert_count += job_insert(job_class)
return insert_count
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_javascript_soup(url)
current_openings = soup.findAll(attrs={"data-tn-element": "jobLink[]"})
job_class = Job(organization, "")
job_class.organization_id = organization_id
insert_count = 0
for current_opening in current_openings:
detail_page_link = current_opening.find('a')['href']
detail_page_soup = get_soup(detail_page_link)
detail_page_desc = detail_page_soup.find(
'div', {"data-tn-component": "jobDescription"})
job_class.title = detail_page_desc.find('h1').text.strip()
job_summary_parts = detail_page_desc.findAll(['p', 'li'])
job_class.summary = ' '.join(
map(lambda a: a.getText(), job_summary_parts[1:-1])).strip()
job_class.location = detail_page_desc.find(
'dt', string="Location").findNext().get_text()
location_parts = job_class.location.split(',')
if len(location_parts) > 1 and len(
location_parts[-1]
) and location_parts[-1].strip().lower() != 'ca':
# skip job if state is not CA
print('Skip location: %s' % job_class.location)
continue
job_class.zip_code = city_to_zip(location_parts[0])
posted_ago = job_summary_parts[-1].get_text().split(' ')
length = posted_ago[1]
if (length[-1:] == '+'):
length = length[:1]
length = int(length)
unit = posted_ago[2]
job_class.post_date = date_ago(length, unit)
job_class.full_or_part = detail_page_desc.find(
'dt', string="Job Type").findNext().get_text()
salary_search = detail_page_desc.find('dt', string="Salary")
if (salary_search is not None):
job_class.salary = salary_search.findNext().get_text()
job_class.info_link = detail_page_link
insert_count += job_insert(job_class)
return insert_count
def run(url):
soup = get_javascript_soup(url)
job_listings = soup.find_all('div', {'class': 'job-listing-job-item'})
job_class = Job(organization, "")
job_class.organization_id = organization_id
insert_count = 0
for job_listing in job_listings:
job_description = job_listing.find_all('span')
# Get job title and link
job_class.title = job_description[0].a.text
job_class.info_link = 'https://recruiting.paylocity.com' + \
job_description[0].a['href']
# 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])
job_class.post_date = datetime(year, month, day)
# Get Location
job_class.location = job_listing.find('div', {
'class': 'location-column'
}).span.text
# Get soup of job listing to scrape more info
listing_soup = get_soup(job_class.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 is not None:
job_class.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(job_class.zip_code) == 0:
job_class.zip_code = globals.city_to_zip(job_class.location)
if 'Status' in listing_body[1].text:
job_class.full_or_part = listing_body[1].text[8:]
if 'Salary' in listing_body[2].text:
job_class.salary = listing_body[2].text[14:]
insert_count += job_insert(job_class)
return insert_count
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):
next_page_url = url
soup = get_javascript_soup_delayed(next_page_url, 'job-table-title')
job_class = Job(organization, "")
job_class.organization_id = organization_id
insert_count = 0
while soup:
job_table = soup.find('tbody')
for job_row in job_table.find_all('tr'):
job_class.title = job_row.find('td', {
'class': 'job-table-title'
}).a.text.strip()
job_class.info_link = 'https://www.governmentjobs.com' + \
job_row.find('td', {'class': 'job-table-title'}).a['href']
job_class.salary = job_row.find('td', {
'class': 'job-table-salary'
}).text
job_class.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(job_class.info_link)
info_container = job_soup.find('div',
{'class': 'summary container'})
job_class.location = clean_location(
info_container.find('div', {
'id': 'location-label-id'
}).parent.find_all('div')[2].text)
job_class.zip_code = city_to_zip(job_class.location)
job_class.summary = job_soup.find('div', {
'id': 'details-info'
}).find('p').text
insert_count += job_insert(job_class)
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
return insert_count
def run(url):
soup = get_javascript_soup(url)
jobs_list = soup.find(
'table', {'id': 'cws-search-results'}).find_all('tr')[1:]
job_class= Job(organization, "")
job_class.organization_id= organization_id
insert_count= 0
for job_entry in jobs_list:
row_cells = job_entry.find_all('td')
job_class.title = row_cells[1].a.text.strip()
job_class.info_link = row_cells[1].a['href']
job_class.location = clean_location(row_cells[2].text)
job_class.zip_code = city_to_zip(job_class.location)
job_soup = get_soup(job_class.info_link)
job_class.full_or_part = job_soup.find(
text="Employment Duration:").parent.parent.b.text.strip()
insert_count+= job_insert(job_class)
return insert_count
def run(url):
# Use Selenium browser to click on all positions button and get soup
options = webdriver.ChromeOptions()
options.add_argument('window-size=800x841')
options.add_argument('headless')
browser = webdriver.Chrome('./chromedriver', chrome_options=options)
browser.get(url)
python_button = browser.find_element_by_id('AllJobs')
python_button.click()
innerHTML = browser.execute_script("return document.body.innerHTML")
soup = BeautifulSoup(innerHTML, "lxml")
browser.quit()
jobs_list = soup.find_all('tr')[2:]
job_class = Job(organization, "")
job_class.organization_id = organization_id
insert_count = 0
for job_entry in jobs_list:
job_details = job_entry.find_all('td')
job_class.title = job_details[0].text.strip()
job_class.info_link = 'https://www5.recruitingcenter.net/Clients/HathawaySycamores/PublicJobs/' + \
job_details[0].a['href']
job_class.full_or_part = job_details[4].text.strip()
location_details = job_details[2].text.strip()
if len(location_details) > 0:
if location_details.isdigit():
job_class.zip_code = int(location_details)
job_class.location = zip_to_city(job_class.zip_code)
else:
job_class.location = location_details
job_class.zip_code = city_to_zip(job_class.location)
else:
job_class.location = ''
job_class.zip_code = ''
insert_count += job_insert(job_class)
return insert_count
def run(url):
soup = get_javascript_soup(url)
job_listings = soup.find_all('div', {'class': 'jobInfo'})
job_class = Job(organization, "")
job_class.organization_id = organization_id
insert_count = 0
for job_listing in job_listings:
job_class.title = job_listing.find('span', {
'class': 'jobTitle'
}).a.text.strip()
job_class.info_link = 'https://www.paycomonline.net' + \
job_listing.find('span', {'class': 'jobTitle'}).a['href']
if job_listing.find('span', {'class': 'jobLocation'}).text:
job_class.location = globals.clean_location(
job_listing.find('span', {
'class': 'jobLocation'
}).text.split(' - ')[1])
job_class.zip_code = globals.city_to_zip(job_class.location)
if job_listing.find('span', {'class': 'jobDescription'}).text:
job_class.summary = job_listing.find('span', {
'class': 'jobDescription'
}).text.strip()
if job_listing.find('span', {'class': 'jobType'}).text:
if ('ft' in str(
job_listing.find('span', {
'class': 'jobType'
}).text).lower()) or ('full' in str(
job_listing.find('span', {
'class': 'jobType'
}).text).lower()):
job_class.full_or_part = 'full'
else:
job_class.full_or_part = 'part'
insert_count += job_insert(job_class)
return insert_count