def main(url, page_number):
program_start_time = time.time()
# cp.change_ip(sudo_password) # change the ip
# Update the executable path of chromedriver in config_webdriver.py if needed
driver = cw.configure_webdriver()
try:
# Get all jobs
data = get_all_jobs(driver, url, page_number)
# Adding timestamp in place of date for uniqueness as it's yet to decide how to name search specific files
filename = '../data/{}-blueskypeople-jobs.csv'
filename = sf.format_filename(filename)
data.to_csv(filename, index=False, header=False)
except Exception as e:
print(str(e))
finally:
driver.close()
# sf.ip_files_cleanup()
seconds = round(time.time() - program_start_time)
minutes = round(seconds / 60, 1)
hours = round(minutes / 60, 1)
print('DONE! ')
print("\n\nRun time = {} seconds; {} minutes; {} hours".format(
seconds, minutes, hours))
def main():
program_start_time = time.time()
driver = cw.configure_webdriver()
try:
parent_url = 'https://mbrdental.co.uk/jobs/'
# cp.change_ip(sudo_password) # change the ip
driver.get(parent_url)
# Get all job urls
jobs = get_all_jobs(driver)
print('Total jobs:', len(jobs))
file_name = '../data/{}-mbrdental-jobs.csv'
file_name = sf.format_filename(file_name)
jobs.to_csv(file_name, index=False, header=False)
except Exception as e:
print(str(e))
finally:
driver.close()
# sf.ip_files_cleanup()
seconds = round(time.time() - program_start_time)
minutes = round(seconds / 60, 1)
hours = round(minutes / 60, 1)
print('DONE! ')
print("\n\nRun time = {} seconds; {} minutes; {} hours".format(
seconds, minutes, hours))
def main():
program_start_time = time.time()
driver = cw.configure_webdriver()
sys_argv = sys.argv
try:
parent_url = 'https://www.diamonddentalstaff.co.uk/careers'
# cp.change_ip() # change the ip
driver.get(parent_url)
# Gets data source from iframe tag
element = driver.find_element_by_name('htmlComp-iframe')
iframe_data_src = element.get_attribute('src')
# Always switch window before requesting a new url using driver
driver.switch_to.window(driver.window_handles[-1])
# Get all job urls
filepath_job_url = sys_argv[1]
print(filepath_job_url)
job_urls = pd.read_csv(filepath_job_url).iloc[:, 0]
print('Total jobs:', len(job_urls))
print('Total unique jobs:', len(set(job_urls)))
if len(job_urls) != 0:
# Get jobs dataframe
data = get_all_jobs(job_urls, driver)
file_name = '../data/{}-diamond-dental-staff-jobs.csv'
file_name = sf.format_filename(file_name)
data.to_csv(file_name, index=False)
else:
print('No jobs found')
except Exception as e:
print(str(e))
finally:
driver.close()
seconds = round(time.time() - program_start_time)
minutes = round(seconds / 60, 1)
hours = round(minutes / 60, 1)
print('DONE! ')
print("\n\nRun time = {} seconds; {} minutes; {} hours".format(
seconds, minutes, hours))
def main(sudo_password):
program_start_time = time.time()
driver = cw.configure_webdriver()
try:
parent_url = 'https://www.diamonddentalstaff.co.uk/careers'
driver.get(parent_url)
# Gets data source from iframe tag
element = driver.find_element_by_name('htmlComp-iframe')
iframe_data_src = element.get_attribute('src')
# Always switch window before requesting a new url using driver
driver.switch_to.window(driver.window_handles[-1])
# Get all job urls
driver.get(iframe_data_src)
job_urls = get_all_job_urls(driver)
print('Total jobs:', len(job_urls))
print('Total unique jobs:', len(set(job_urls)))
if len(job_urls) != 0:
# Get jobs dataframe
file_name = '../data/' + '{}-diamond-dental-staff-job-url.csv'
file_name = sf.format_filename(file_name)
pd.Series(job_urls).to_csv(file_name, index=False,header=False)
print('\tJob urls stored for diamond-dental-staff.')
else:
print('No jobs found')
except Exception as e:
print(str(e))
finally:
driver.close()
# sf.ip_files_cleanup()
seconds = round(time.time() - program_start_time)
minutes = round(seconds/60, 1)
hours = round(minutes/60, 1)
print('DONE! ')
print("\n\nRun time = {} seconds; {} minutes; {} hours".format(seconds, minutes, hours))
def main():
program_start_time = time.time()
driver = cw.configure_webdriver()
try:
parent_url = 'https://portal.brownslocumlink.com/Jobs/Results.aspx?JobResults=1'
# cp.change_ip(sudo_password) # change the ip
driver.get(parent_url)
# Get all job urls
job_urls = get_all_job_urls(driver)
print('Total jobs:', len(job_urls))
print('Total unique jobs:', len(set(job_urls)))
job_urls = list(set(job_urls))
if len(job_urls) != 0:
# Get jobs dataframe
data = get_all_jobs(job_urls, driver)
print(data)
file_name = '../data/{}-brownslocum-jobs.csv'
file_name = sf.format_filename(file_name)
data.to_csv(file_name, index=False, header=False)
else:
print('No jobs found')
except Exception as e:
print(str(e))
finally:
driver.close()
# sf.ip_files_cleanup()
seconds = round(time.time() - program_start_time)
minutes = round(seconds / 60, 1)
hours = round(minutes / 60, 1)
print('DONE! ')
print("\n\nRun time = {} seconds; {} minutes; {} hours".format(
seconds, minutes, hours))
def main():
program_start_time = time.time()
driver = cw.configure_webdriver()
sys_argv = sys.argv
try:
parent_url = 'https://www.dentalelite.co.uk/jobs/'
driver.get(parent_url)
# Get all job urls
filepath_job_url = sys_argv[1]
print(filepath_job_url)
job_urls = pd.read_csv(filepath_job_url).iloc[:, 0]
print('Total jobs:', len(job_urls))
print('Total unique jobs:', len(set(job_urls)))
job_urls = list(set(job_urls))
if len(job_urls) != 0:
# Get jobs dataframe
data = get_all_jobs(job_urls, driver)
file_name = '../data/{}-dental-elite-jobs.csv'
file_name = sf.format_filename(file_name)
data.to_csv(file_name, index=False)
else:
print('No jobs found')
except Exception as e:
print(str(e))
finally:
driver.close()
seconds = round(time.time() - program_start_time)
minutes = round(seconds / 60, 1)
hours = round(minutes / 60, 1)
print('DONE! ')
print("\n\nRun time = {} seconds; {} minutes; {} hours".format(
seconds, minutes, hours))
def main():
program_start_time = time.time()
# Update the executable path of chromedriver in config_webdriver.py if needed
driver = cw.configure_webdriver()
sys_argv = sys.argv
try:
parent_url = "https://www.tempdent.co.uk/jobs"
driver.get(parent_url)
# Get all job urls
filepath_job_url = sys_argv[1]
print(filepath_job_url)
job_urls = pd.read_csv(filepath_job_url).iloc[:, 0]
print('Total jobs:', len(jobs))
print('Total unique jobs:', len(set(jobs)))
jobs = list(set(jobs))
if len(job_urls) != 0:
data = get_all_jobs(job_urls, driver)
filename = '../data/{}-tempdent-jobs.csv'
filename = sf.format_filename(filename)
data.to_csv(filename, index=False)
else:
print('No jobs')
except Exception as e:
print(str(e))
finally:
driver.close()
seconds = round(time.time() - program_start_time)
minutes = round(seconds / 60, 1)
hours = round(minutes / 60, 1)
print('DONE! ')
print("\n\nRun time = {} seconds; {} minutes; {} hours".format(
seconds, minutes, hours))
def main():
program_start_time = time.time()
driver = cw.configure_webdriver()
try:
parent_url = 'https://www.dentalelite.co.uk/jobs/'
# cp.change_ip(sudo_password) # change the ip
driver.get(parent_url)
# Get all job urls
job_urls = get_all_job_urls(driver)
print('Total jobs:', len(job_urls))
print('Total unique jobs:', len(set(job_urls)))
job_urls = list(set(job_urls))
if len(job_urls) != 0:
# Get jobs dataframe
file_name = '../data/' + '{}-dental-elite-job-url.csv'
file_name = sf.format_filename(file_name)
pd.Series(job_urls).to_csv(file_name, index=False, header=False)
print('\tJob urls stored for dental-elite.')
else:
print('No jobs found')
except Exception as e:
print(str(e))
finally:
driver.close()
# Remove the command file
# sf.ip_files_cleanup()
seconds = round(time.time() - program_start_time)
minutes = round(seconds / 60, 1)
hours = round(minutes / 60, 1)
print('DONE! ')
print("\n\nRun time = {} seconds; {} minutes; {} hours".format(
seconds, minutes, hours))
def main():
program_start_time = time.time()
# Update the executable path of chromedriver in config_webdriver.py if needed
driver = cw.configure_webdriver()
# cp.change_ip(sudo_password) # change the ip
try:
parent_url = "https://www.tempdent.co.uk/jobs"
driver.get(parent_url)
# Get all job urls
job_urls = list(set(get_all_job_urls(driver, parent_url)))
print('Total jobs:', len(job_urls))
print('Total unique jobs:', len(set(job_urls)))
job_urls = list(set(job_urls))
if len(job_urls) != 0:
# Get jobs dataframe
file_name = '../data/' + '{}-tempdent-job-url.csv'
file_name = sf.format_filename(file_name)
pd.Series(job_urls).to_csv(file_name, index=False, header=False)
print('\tJob urls stored for tempdent.')
else:
print('No jobs')
except Exception as e:
print(str(e))
finally:
driver.close()
# sf.ip_files_cleanup()
seconds = round(time.time() - program_start_time)
minutes = round(seconds / 60, 1)
hours = round(minutes / 60, 1)
print('DONE! ')
print("\n\nRun time = {} seconds; {} minutes; {} hours".format(
seconds, minutes, hours))
def main():
program_start_time = time.time()
driver = cw.configure_webdriver()
try:
url = 'https://www.medicruit.co.uk/dental-jobs/?position-type=&location=&work-type=-1&position-date=-1&page='
# cp.change_ip(sudo_password) # change the ip
driver.switch_to.window(driver.window_handles[-1])
driver.get(url + str(1))
pages = driver.find_element_by_class_name('pagination')
total_pages = int(
pages.find_elements_by_tag_name('a')[-1].get_attribute(
'href').split('page=')[1])
print('Total pages:', str(total_pages))
data = get_all_jobs(driver, total_pages, url)
file_name = '../data/{}-medcruit-jobs.csv'
file_name = sf.format_filename(file_name)
data.to_csv(file_name, index=False, header=False)
except Exception as e:
print(str(e))
finally:
driver.close()
# sf.ip_files_cleanup()
seconds = round(time.time() - program_start_time)
minutes = round(seconds / 60, 1)
hours = round(minutes / 60, 1)
print('DONE! ')
print("\n\nRun time = {} seconds; {} minutes; {} hours".format(
seconds, minutes, hours))
jobs_dataframe = jobs_dataframe.append(df, sort=False)
time.sleep(random.randint(1, 4))
except Exception as e:
print(str(e))
time.sleep(random.randint(1, 4))
return jobs_dataframe
if __name__ == '__main__':
try:
program_start_time = time.time()
driver = cw.configure_webdriver()
driver.switch_to.window(driver.window_handles[-1])
filepath_job_url = sys_argv[1]
print(filepath_job_url)
search_term = filepath_job_url.split('url')[-1].split('.')[0][1:]
job_urls = pd.read_csv(filepath_job_url).iloc[:,0]
if len(job_urls) != 0:
print('Total jobs for {}: {}'.format(search_term, len(job_urls)))
data = get_all_jobs(job_urls, driver, search_term)
file_name = '../data/' + '{}-indeed-jobs-' + search_term + '.csv'
file_name = sf.format_filename(file_name)
data.to_csv(file_name, index=False)
print('Data stored for: {}. shape = {}'.format(search_term, data.shape))
def main(job_title_list):
program_start_time = time.time()
# Update the executable path of chromedriver in config_webdriver.py if needed
driver = cw.configure_webdriver()
# cp.change_ip(sudo_password) # change the ip
try:
for i in range(len(job_title_list)):
job_url_list = []
parent_url = 'https://www.indeed.co.uk/jobs?q=' + job_title_list[
i] + '&l=United+Kingdom'
print('\n\nSearch term:', job_title_list[i])
start = time.time()
driver.switch_to.window(driver.window_handles[-1])
driver.get(parent_url)
# Get all job urls
job_url_list = get_all_job_urls(driver)
job_url_list = list(set(job_url_list))
print('\tTotal jobs for {}: {}'.format(job_title_list[i],
len(set(job_url_list))))
print('\tTotal unique jobs for {}: {}'.format(
job_title_list[i], len(set(job_url_list))))
if len(job_url_list) != 0:
# Get jobs dataframe
file_name = '../data/' + '{}-indeed-job-url-' + job_title_list[
i].replace('+', '-') + '.csv'
file_name = sf.format_filename(file_name)
pd.Series(job_url_list).to_csv(file_name,
index=False,
header=False)
print('\tJob urls stored for:', job_title_list[i])
else:
print('No jobs found for search term', job_title_list[i])
seconds = round(time.time() - start)
minutes = round(seconds / 60, 1)
hours = round(minutes / 60, 1)
print(
"\tRun time for {} = {} seconds; {} minutes; {} hours.\n\n\n".
format(job_title_list[i], seconds, minutes, hours))
except Exception as e:
print(str(e))
finally:
driver.close()
# sf.ip_files_cleanup()
seconds = round(time.time() - program_start_time)
minutes = round(seconds / 60, 1)
hours = round(minutes / 60, 1)
print('DONE! ')
print(
"\n\nRun time for all job searches on indeed = {} seconds; {} minutes; {} hours"
.format(seconds, minutes, hours))
