def get_company_profile(cookie,company_id,keyword):
if keyword == None:
url='https://www.linkedin.com/voyager/api/search/cluster?count=40&guides=List(v->PEOPLE,facetCurrentCompany->%s)&origin=OTHER&q=guided&start=0' % company_id
else:
url = "https://www.linkedin.com/voyager/api/search/cluster?count=40&guides=List(v->PEOPLE,facetCurrentCompany->%s)&keywords=%s&origin=OTHER&q=guided&start=0" % (company_id,keyword)
data=http.connect(url,cookie)
if data == None:
logger.red('Unable to authenticate to LinkedIn')
quit()
return data.text
def company_profile(cookie,company_id,keyword):
# This function requests the companies profile and returns the data
if keyword == None:
url='https://www.linkedin.com/voyager/api/search/cluster?count=40&guides=List(v->PEOPLE,facetCurrentCompany->%s)&origin=OTHER&q=guided&start=0' % company_id
logger.debug('Requesting %s from company_profile()' % url)
else:
url = "https://www.linkedin.com/voyager/api/search/cluster?count=40&guides=List(v->PEOPLE,facetCurrentCompany->%s)&keywords=%s&origin=OTHER&q=guided&start=0" % (company_id,keyword)
logger.debug('Requesting %s from company_profile()' % url)
data=http.connect(url,cookie)
if data == None:
logger.red('Unable to authenticate to LinkedIn')
quit()
return data.text
def user_data(results, pages, cookie, company_id, domain, email_format):
# Every page returns a dictionary of data, each dictionary is added to this list.
users_per_page = []
for page in range(0, pages + 1):
if page + 1 == 25:
break
if results < 40:
# This method pulls 40 results per page. If the available results is less then 40
# Set results_per_age to whatever the number is
results_per_page = results
results_to_fetch = results
else:
# However, if the amount of available results is higher than the per page limit, set the per page limit to the max (40)
results_per_page = 40
# Every time this is hit, the start point in the api is incremented. First, it gets 0 - 40, then 40 - 80 and so on.
# This can be dynamically figured out by multiplying the page number (1) by the results_per_page (40).
results_to_fetch = results_per_page * page
# In order to stop this loop from requesting more than is available, and then breaking it, this if statement limits that:
if results_to_fetch >= results:
break
url = "https://www.linkedin.com/voyager/api/search/cluster?count=40&guides=List(v->PEOPLE,facetCurrentCompany->%s)&origin=OTHER&q=guided&start=%s" % (
company_id, results_to_fetch)
logger.blue('Pulling from page %s' % logger.BLUE(page))
data = http.connect(url, cookie)
result = data.text.encode('UTF-8')
try:
result = json.loads(result)
except Exception as e:
x = str(e)
logger.red(e)
quit()
users = extract_data(result, domain, email_format)
users_per_page.append(users)
return users_per_page
def get_users(data,pages,total_employees,keyword):
#Grab the user data per page
cookie = data.cookie
company_id = data.company_id
email_format = data.email_format
keyword = data.keyword
domain = data.domain
validation = data.validation
api_key = data.api_key
# Every page returns a dictionary of data, each dictionary is added to this list.
people_on_this_page=0
logger.debug(str(vars(data)))
userdata_per_page = []
for page in range(0,pages+1):
if page+1 == 25:
logger.debug('Breaking, pages exceed 25')
break
if total_employees < 40:
logger.debug('Locking users per page to match total_employees')
# This method pulls 40 total_employees per page. If the available total_employees is less then 40
# Set total_employees_per_age to whatever the number is
total_employees_per_page = total_employees
total_employees_to_fetch = total_employees
else:
logger.debug('Locking users per page to 40')
# However, if the amount of available total_employees is higher than the per page limit, set the per page limit to the max (40)
total_employees_per_page = 40
# Every time this is hit, the start point in the api is incremented. First, it gets 0 - 40, then 40 - 80 and so on.
# This can be dynamically figured out by multiplying the page number (1) by the total_employees_per_page (40).
total_employees_to_fetch = total_employees_per_page * page
# In order to stop this loop from requesting more than is available, and then breaking it, this if statement limits that:
if total_employees_to_fetch >= total_employees:
break
# Loop over pages
if keyword == None:
# Experimental if statement, this request should work at this point(?)
logger.debug('No keyword set [getting user per page]')
url = "https://www.linkedin.com/voyager/api/search/cluster?count=40&guides=List(v->PEOPLE,facetCurrentCompany->%s)&origin=OTHER&q=guided&start=%s" % (company_id,total_employees_to_fetch)
else:
# In theory, this will only grab users per page with the keyword
logger.debug('Using keyword %s' % logger.MAGENTA(keyword))
url = "https://www.linkedin.com/voyager/api/search/cluster?count=40&guides=List(v->PEOPLE,facetCurrentCompany->%s)&keywords=%s&origin=OTHER&q=guided&start=%s" % (company_id,keyword,total_employees_to_fetch)
logger.debug('Requesting %s from get_users()' % url)
logger.blue('Pulling from page %s' % logger.BLUE(page+1))
api_response=http.connect(url,cookie)
result = api_response.text.encode('UTF-8')
try:
result = json.loads(result) #contains data for ~40 people
except Exception as e:
print(e)
quit()
people_on_this_page=people_on_this_page+len(result['elements'][0]['elements'])
if people_on_this_page > 0:
logger.green('Successfully pulled %s users' % logger.GREEN(str(people_on_this_page)))
userdata_per_page.append(result)
# This part could do with threading
users = parse_users(data,userdata_per_page,total_employees)
logger.debug('Sending list of json objects to parse_users()')
return users