linkedin-scraper 2.1.0__tar.gz

usr/lib/python3.6/site-packages/linkedin_scraper/__init__.py

@@ -0,0 +1,10 @@
+from os.path import dirname, basename, isfile
+from .person import Person
+from .objects import Institution, Experience, Education
+from .company import Company
+
+__version__ = "2.1.0"
+
+import glob
+modules = glob.glob(dirname(__file__)+"/*.py")
+__all__ = [ basename(f)[:-3] for f in modules if isfile(f) and not f.endswith('__init__.py')]

usr/lib/python3.6/site-packages/linkedin_scraper/company.py

@@ -0,0 +1,213 @@
+import requests
+from lxml import html
+from selenium import webdriver
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from .objects import Scraper
+import os
+
+class CompanySummary(object):
+    linkedin_url = None
+    name = None
+    followers = None
+
+    def __init__(self, linkedin_url = None, name = None, followers = None):
+        self.linkedin_url = linkedin_url
+        self.name = name
+        self.followers = followers
+
+    def __repr__(self):
+        if self.followers == None:
+            return """ {name} """.format(name = self.name)
+        else:
+            return """ {name} {followers} """.format(name = self.name, followers = self.followers)
+
+class Company(Scraper):
+    linkedin_url = None
+    name = None
+    about_us =None
+    website = None
+    headquarters = None
+    founded = None
+    company_type = None
+    company_size = None
+    specialties = None
+    showcase_pages =[]
+    affiliated_companies = []
+
+    def __init__(self, linkedin_url = None, name = None, about_us =None, website = None, headquarters = None, founded = None, company_type = None, company_size = None, specialties = None, showcase_pages =[], affiliated_companies = [], driver = None, scrape = True):
+        self.linkedin_url = linkedin_url
+        self.name = name
+        self.about_us = about_us
+        self.website = website
+        self.headquarters = headquarters
+        self.founded = founded
+        self.company_type = company_type
+        self.company_size = company_size
+        self.specialties = specialties
+        self.showcase_pages = showcase_pages
+        self.affiliated_companies = affiliated_companies
+
+        if driver is None:
+            try:
+                if os.getenv("CHROMEDRIVER") == None:
+                    driver_path = os.path.join(os.path.dirname(__file__), 'drivers/chromedriver')
+                else:
+                    driver_path = os.getenv("CHROMEDRIVER")
+
+                driver = webdriver.Chrome(driver_path)
+            except:
+                driver = webdriver.Chrome()
+
+        driver.get(linkedin_url)
+        self.driver = driver
+
+        if scrape:
+            self.scrape()
+
+    def __get_text_under_subtitle(self, elem):
+        return "\n".join(elem.text.split("\n")[1:])
+
+    def __get_text_under_subtitle_by_class(self, driver, class_name):
+        return self.__get_text_under_subtitle(driver.find_element_by_class_name(class_name))
+
+    def scrape(self, close_on_complete = True):
+        if self.is_signed_in():
+            self.scrape_logged_in(close_on_complete = close_on_complete)
+        else:
+            self.scrape_not_logged_in(close_on_complete = close_on_complete)
+
+    def scrape_logged_in(self, close_on_complete = True):
+        driver = self.driver
+
+        self.name = driver.find_element_by_xpath('//h1[@dir="ltr"]').text
+        self.about_us = driver.find_element_by_class_name("org-about-us-organization-description__text").text
+
+        self.specialties = "\n".join(driver.find_element_by_class_name("org-about-company-module__specialities").text.split(", "))
+        self.website = driver.find_element_by_class_name("org-about-us-company-module__website").text
+        self.headquarters = driver.find_element_by_class_name("org-about-company-module__headquarters").text
+        self.industry = driver.find_element_by_class_name("company-industries").text
+        self.company_size = driver.find_element_by_class_name("org-about-company-module__company-staff-count-range").text
+
+        driver.execute_script("window.scrollTo(0, Math.ceil(document.body.scrollHeight/2));")
+
+
+        try:
+            _ = WebDriverWait(driver, 3).until(EC.presence_of_element_located((By.CLASS_NAME, 'company-list')))
+            showcase, affiliated = driver.find_elements_by_class_name("company-list")
+            driver.find_element_by_id("org-related-companies-module__show-more-btn").click()
+
+            # get showcase
+            for showcase_company in showcase.find_elements_by_class_name("org-company-card"):
+                companySummary = CompanySummary(
+                        linkedin_url = showcase_company.find_element_by_class_name("company-name-link").get_attribute("href"),
+                        name = showcase_company.find_element_by_class_name("company-name-link").text,
+                        followers = showcase_company.find_element_by_class_name("company-followers-count").text
+                    )
+                self.showcase_pages.append(companySummary)
+
+            # affiliated company
+
+            for affiliated_company in showcase.find_elements_by_class_name("org-company-card"):
+                companySummary = CompanySummary(
+                         linkedin_url = affiliated_company.find_element_by_class_name("company-name-link").get_attribute("href"),
+                        name = affiliated_company.find_element_by_class_name("company-name-link").text,
+                        followers = affiliated_company.find_element_by_class_name("company-followers-count").text
+                        )
+                self.affiliated_companies.append(companySummary)
+
+        except:
+            pass
+
+
+        if close_on_complete:
+            driver.close()
+
+    def scrape_not_logged_in(self, close_on_complete = True, retry_limit = 10):
+        driver = self.driver
+        retry_times = 0
+        while self.is_signed_in() and retry_times <= retry_limit:
+            page = driver.get(self.linkedin_url)
+            retry_times = retry_times + 1
+
+        self.name = driver.find_element_by_class_name("name").text
+
+        self.about_us = driver.find_element_by_class_name("basic-info-description").text
+        self.specialties = self.__get_text_under_subtitle_by_class(driver, "specialties")
+        self.website = self.__get_text_under_subtitle_by_class(driver, "website")
+        self.headquarters = driver.find_element_by_class_name("adr").text
+        self.industry = driver.find_element_by_class_name("industry").text
+        self.company_size = driver.find_element_by_class_name("company-size").text
+        self.company_type = self.__get_text_under_subtitle_by_class(driver, "type")
+        self.founded = self.__get_text_under_subtitle_by_class(driver, "founded")
+
+        # get showcase
+        try:
+            driver.find_element_by_id("view-other-showcase-pages-dialog").click()
+            WebDriverWait(driver, 3).until(EC.presence_of_element_located((By.ID, 'dialog')))
+
+            showcase_pages = driver.find_elements_by_class_name("company-showcase-pages")[1]
+            for showcase_company in showcase_pages.find_elements_by_tag_name("li"):
+                name_elem = showcase_company.find_element_by_class_name("name")
+                companySummary = CompanySummary(
+                    linkedin_url = name_elem.find_element_by_tag_name("a").get_attribute("href"),
+                    name = name_elem.text,
+                    followers = showcase_company.text.split("\n")[1]
+                )
+                self.showcase_pages.append(companySummary)
+            driver.find_element_by_class_name("dialog-close").click()
+        except:
+            pass
+
+        # affiliated company
+        try:
+            affiliated_pages = driver.find_element_by_class_name("affiliated-companies")
+            for i, affiliated_page in enumerate(affiliated_pages.find_elements_by_class_name("affiliated-company-name")):
+                if i % 3 == 0:
+                    affiliated_pages.find_element_by_class_name("carousel-control-next").click()
+
+                companySummary = CompanySummary(
+                    linkedin_url = affiliated_page.find_element_by_tag_name("a").get_attribute("href"),
+                    name = affiliated_page.text
+                )
+                self.affiliated_companies.append(companySummary)
+        except:
+            pass
+
+        if close_on_complete:
+            driver.close()
+
+    def __repr__(self):
+        return """
+{name}
+
+{about_us}
+
+Specialties: {specialties}
+
+Website: {website}
+Industry: {industry}
+Type: {company_type}
+Headquarters: {headquarters}
+Company Size: {company_size}
+Founded: {founded}
+
+Showcase Pages
+{showcase_pages}
+
+Affiliated Companies
+{affiliated_companies}
+    """.format(
+        name = self.name,
+        about_us = self.about_us,
+        specialties = self.specialties,
+        website= self.website,
+        industry= self.industry,
+        company_type= self.company_type,
+        headquarters= self.headquarters,
+        company_size= self.company_size,
+        founded= self.founded,
+        showcase_pages = self.showcase_pages,
+        affiliated_companies = self.affiliated_companies
+    )

usr/lib/python3.6/site-packages/linkedin_scraper/functions.py

@@ -0,0 +1,15 @@
+import re
+
+def time_divide(string):
+    duration = re.search("\((.*?)\)", string)
+
+    if duration != None:
+        duration = duration.group(0)
+        string = string.replace(duration, "").strip()
+    else:
+        duration = "()"
+
+    times = string.split("–")
+    return (times[0].strip(), times[1].strip(), duration[1:-1])
+
+

usr/lib/python3.6/site-packages/linkedin_scraper/objects.py

@@ -0,0 +1,60 @@
+
+class Institution(object):
+    institution_name = None
+    website = None
+    industry = None
+    type = None
+    headquarters = None
+    company_size = None
+    founded = None
+
+    def __init__(self, name=None, website=None, industry=None, type=None, headquarters=None, company_size=None, founded=None):
+        self.name = name
+        self.website = website
+        self.industry = industry
+        self.type = type
+        self.headquarters = headquarters
+        self.company_size = company_size
+        self.founded = founded
+
+class Experience(Institution):
+    from_date = None
+    to_date = None
+    description = None
+    position_title = None
+
+    def __init__(self, from_date = None, to_date = None, description = None, position_title = None):
+        self.from_date = from_date
+        self.to_date = to_date
+        self.description = description
+        self.position_title = position_title
+
+    def __repr__(self):
+        return "{position_title} at {company} from {from_date} to {to_date}".format( from_date = self.from_date, to_date = self.to_date, position_title = self.position_title, company = self.institution_name)
+
+
+class Education(Institution):
+    from_date = None
+    to_date = None
+    description = None
+    degree = None
+
+    def __init__(self, from_date = None, to_date = None, description = None, degree = None):
+        self.from_date = from_date
+        self.to_date = to_date
+        self.description = description
+        self.degree = degree
+
+    def __repr__(self):
+        return "{degree} at {company} from {from_date} to {to_date}".format( from_date = self.from_date, to_date = self.to_date, degree = self.degree, company = self.institution_name)
+
+class Scraper(object):
+    driver = None
+
+    def is_signed_in(self):
+        try:
+            self.driver.find_element_by_id("profile-nav-item")
+            return True
+        except:
+            pass
+        return False

usr/lib/python3.6/site-packages/linkedin_scraper/person.py

@@ -0,0 +1,145 @@
+import requests
+from lxml import html
+from selenium import webdriver
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from .functions import time_divide
+from .objects import Experience, Education, Scraper
+import os
+
+class Person(Scraper):
+    name = None
+    experiences = []
+    educations = []
+    also_viewed_urls = []
+    linkedin_url = None
+
+    def __init__(self, linkedin_url = None, experiences = [], educations = [], driver = None, scrape = True):
+        self.linkedin_url = linkedin_url
+        self.experiences = experiences
+        self.educations = educations
+
+        if driver is None:
+            try:
+                if os.getenv("CHROMEDRIVER") == None:
+                    driver_path = os.path.join(os.path.dirname(__file__), 'drivers/chromedriver')
+                else:
+                    driver_path = os.getenv("CHROMEDRIVER")
+
+                driver = webdriver.Chrome(driver_path)
+            except:
+                driver = webdriver.Chrome()
+
+        driver.get(linkedin_url)
+        self.driver = driver
+
+        if scrape:
+            self.scrape()
+
+
+    def add_experience(self, experience):
+        self.experiences.append(experience)
+
+    def add_education(self, education):
+        self.educations.append(education)
+
+    def scrape(self, close_on_complete = True):
+        if self.is_signed_in():
+            self.scrape_logged_in(close_on_complete = close_on_complete)
+        else:
+            self.scrape_not_logged_in(close_on_complete = close_on_complete)
+
+    def scrape_logged_in(self, close_on_complete = True):
+        driver = self.driver
+        self.name = driver.find_element_by_class_name("pv-top-card-section__name").text
+
+        driver.execute_script("window.scrollTo(0, Math.ceil(document.body.scrollHeight/2));")
+
+        _ = WebDriverWait(driver, 3).until(EC.presence_of_element_located((By.ID, "experience-section")))
+
+        # get experience
+        exp = driver.find_element_by_id("experience-section")
+        for position in exp.find_elements_by_class_name("pv-position-entity"):
+            position_title = position.find_element_by_tag_name("h3").text
+            company = position.find_element_by_class_name("pv-entity__secondary-title").text
+
+            try:
+                times = position.find_element_by_class_name("pv-entity__date-range").text
+                from_date, to_date, duration = time_divide(times)
+            except:
+                from_date, to_date = (None, None)
+            experience = Experience( position_title = position_title , from_date = from_date , to_date = to_date)
+            experience.institution_name = company
+            self.add_experience(experience)
+
+        driver.execute_script("window.scrollTo(0, Math.ceil(document.body.scrollHeight/1.5));")
+
+        _ = WebDriverWait(driver, 3).until(EC.presence_of_element_located((By.ID, "education-section")))
+
+        # get education
+        edu = driver.find_element_by_id("education-section")
+        for school in edu.find_elements_by_class_name("pv-profile-section__sortable-item"):
+            university = school.find_element_by_class_name("pv-entity__school-name").text
+            degree = school.find_element_by_class_name("pv-entity__degree-name").text
+            try:
+                times = school.find_element_by_class_name("pv-entity__dates").text
+                from_date, to_date, duration = time_divide(times)
+            except:
+                from_date, to_date = (None, None)
+            education = Education(from_date = from_date, to_date = to_date, degree=degree)
+            education.institution_name = university
+            self.add_education(education)
+
+        if close_on_complete:
+            driver.close()
+
+
+    def scrape_not_logged_in(self, close_on_complete=True, retry_limit = 10):
+        driver = self.driver
+        retry_times = 0
+        while self.is_signed_in() and retry_times <= retry_limit:
+            page = driver.get(self.linkedin_url)
+            retry_times = retry_times + 1
+
+
+        # get name
+        self.name = driver.find_element_by_id("name").text
+
+        # get experience
+        exp = driver.find_element_by_id("experience")
+        for position in exp.find_elements_by_class_name("position"):
+            position_title = position.find_element_by_class_name("item-title").text
+            company = position.find_element_by_class_name("item-subtitle").text
+
+            try:
+                times = position.find_element_by_class_name("date-range").text
+                from_date, to_date, duration = time_divide(times)
+            except:
+                from_date, to_date = (None, None)
+            experience = Experience( position_title = position_title , from_date = from_date , to_date = to_date)
+            experience.institution_name = company
+            self.add_experience(experience)
+
+        # get education
+        edu = driver.find_element_by_id("education")
+        for school in edu.find_elements_by_class_name("school"):
+            university = school.find_element_by_class_name("item-title").text
+            degree = school.find_element_by_class_name("original").text
+            try:
+                times = school.find_element_by_class_name("date-range").text
+                from_date, to_date, duration = time_divide(times)
+            except:
+                from_date, to_date = (None, None)
+            education = Education(from_date = from_date, to_date = to_date, degree=degree)
+            education.institution_name = university
+            self.add_education(education)
+
+        # get 
+        if close_on_complete:
+            driver.close()
+
+    def __repr__(self):
+        return "{name}\n\nExperience\n{exp}\n\nEducation\n{edu}".format(name = self.name, exp = self.experiences, edu = self.educations)
+
+

usr/lib/python3.6/site-packages/linkedin_scraper/scraper.py

@@ -0,0 +1,8 @@
+#!/usr/bin/python3
+
+import requests
+from lxml import html
+from selenium import webdriver
+import re
+import os
+

usr/lib/python3.6/site-packages/linkedin_scraper-2.1.0-py3.6.egg-info/PKG-INFO

@@ -0,0 +1,13 @@
+Metadata-Version: 1.1
+Name: linkedin-scraper
+Version: 2.1.0
+Summary: Scrapes user data from Linkedin
+Home-page: https://github.com/joeyism/linkedin_scraper
+Author: Joey Sham
+Author-email: sham.joey@gmail.com
+License: UNKNOWN
+Download-URL: https://github.com/joeyism/linkedin_scraper/dist/2.1.0.tar.gz
+Description-Content-Type: UNKNOWN
+Description: UNKNOWN
+Keywords: linkedin,scraping,scraper
+Platform: UNKNOWN

usr/lib/python3.6/site-packages/linkedin_scraper-2.1.0-py3.6.egg-info/SOURCES.txt

@@ -0,0 +1,14 @@
+README.rst
+setup.cfg
+setup.py
+linkedin_scraper/__init__.py
+linkedin_scraper/company.py
+linkedin_scraper/functions.py
+linkedin_scraper/objects.py
+linkedin_scraper/person.py
+linkedin_scraper/scraper.py
+linkedin_scraper.egg-info/PKG-INFO
+linkedin_scraper.egg-info/SOURCES.txt
+linkedin_scraper.egg-info/dependency_links.txt
+linkedin_scraper.egg-info/requires.txt
+linkedin_scraper.egg-info/top_level.txt

usr/lib/python3.6/site-packages/linkedin_scraper-2.1.0-py3.6.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

usr/lib/python3.6/site-packages/linkedin_scraper-2.1.0-py3.6.egg-info/requires.txt

@@ -0,0 +1,3 @@
+lxml
+request
+selenium

usr/lib/python3.6/site-packages/linkedin_scraper-2.1.0-py3.6.egg-info/top_level.txt

@@ -0,0 +1 @@
+linkedin_scraper

usr/lib/python3.6/site-packages/linkedin_user_scraper/__init__.py

@@ -0,0 +1,8 @@
+from os.path import dirname, basename, isfile
+from .person import Person
+from .objects import Institution, Experience, Education
+from .company import Company
+
+import glob
+modules = glob.glob(dirname(__file__)+"/*.py")
+__all__ = [ basename(f)[:-3] for f in modules if isfile(f) and not f.endswith('__init__.py')]

usr/lib/python3.6/site-packages/linkedin_user_scraper/company.py

@@ -0,0 +1,159 @@
+import requests
+from lxml import html
+from selenium import webdriver
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+import os
+
+class CompanySummary(object):
+    linkedin_url = None
+    name = None
+    followers = None
+
+    def __init__(self, linkedin_url = None, name = None, followers = None):
+        self.linkedin_url = linkedin_url
+        self.name = name
+        self.followers = followers
+
+    def __repr__(self):
+        if self.followers == None:
+            return """ {name} """.format(name = self.name)
+        else:
+            return """ {name} {followers} """.format(name = self.name, followers = self.followers)
+
+class Company(object):
+    linkedin_url = None
+    name = None
+    about_us =None
+    website = None
+    headquarters = None
+    founded = None
+    company_type = None
+    company_size = None
+    specialties = None
+    showcase_pages =[]
+    affiliated_companies = []
+    driver = None
+
+    def __init__(self, linkedin_url = None, name = None, about_us =None, website = None, headquarters = None, founded = None, company_type = None, company_size = None, specialties = None, showcase_pages =[], affiliated_companies = [], driver = None, scrape = True):
+        self.linkedin_url = linkedin_url
+        self.name = name
+        self.about_us = about_us
+        self.website = website
+        self.headquarters = headquarters
+        self.founded = founded
+        self.company_type = company_type
+        self.company_size = company_size
+        self.specialties = specialties
+        self.showcase_pages = showcase_pages
+        self.affiliated_companies = affiliated_companies
+
+        if driver is None:
+            try:
+                if os.getenv("CHROMEDRIVER") == None:
+                    driver_path = os.path.join(os.path.dirname(__file__), 'drivers/chromedriver')
+                else:
+                    driver_path = os.getenv("CHROMEDRIVER")
+
+                driver = webdriver.Chrome(driver_path)
+            except:
+                driver = webdriver.Chrome()
+
+        driver.get(linkedin_url)
+        self.driver = driver
+
+        if scrape:
+            self.scrape()
+
+    def __get_text_under_subtitle(self, elem):
+        return "\n".join(elem.text.split("\n")[1:])
+
+    def __get_text_under_subtitle_by_class(self, driver, class_name):
+        return self.__get_text_under_subtitle(driver.find_element_by_class_name(class_name))
+
+
+    def scrape(self, close_on_complete = True):
+        driver = self.driver
+        page = driver.get(self.linkedin_url)
+
+        self.name = driver.find_element_by_class_name("name").text
+
+        self.about_us = driver.find_element_by_class_name("basic-info-description").text
+        self.specialties = self.__get_text_under_subtitle_by_class(driver, "specialties")
+        self.website = self.__get_text_under_subtitle_by_class(driver, "website")
+        self.headquarters = driver.find_element_by_class_name("adr").text
+        self.industry = driver.find_element_by_class_name("industry").text
+        self.company_size = driver.find_element_by_class_name("company-size").text
+        self.company_type = self.__get_text_under_subtitle_by_class(driver, "type")
+        self.founded = self.__get_text_under_subtitle_by_class(driver, "founded")
+
+        # get showcase
+        try:
+            driver.find_element_by_id("view-other-showcase-pages-dialog").click()
+            WebDriverWait(driver, 3).until(EC.presence_of_element_located((By.ID, 'dialog')))
+
+            showcase_pages = driver.find_elements_by_class_name("company-showcase-pages")[1]
+            for showcase_company in showcase_pages.find_elements_by_tag_name("li"):
+                name_elem = showcase_company.find_element_by_class_name("name")
+                companySummary = CompanySummary(
+                    linkedin_url = name_elem.find_element_by_tag_name("a").get_attribute("href"),
+                    name = name_elem.text,
+                    followers = showcase_company.text.split("\n")[1]
+                )
+                self.showcase_pages.append(companySummary)
+            driver.find_element_by_class_name("dialog-close").click()
+        except:
+            pass
+
+        # affiliated company
+        try:
+            affiliated_pages = driver.find_element_by_class_name("affiliated-companies")
+            for i, affiliated_page in enumerate(affiliated_pages.find_elements_by_class_name("affiliated-company-name")):
+                if i % 3 == 0:
+                    affiliated_pages.find_element_by_class_name("carousel-control-next").click()
+
+                companySummary = CompanySummary(
+                    linkedin_url = affiliated_page.find_element_by_tag_name("a").get_attribute("href"),
+                    name = affiliated_page.text
+                )
+                self.affiliated_companies.append(companySummary)
+        except:
+            pass
+
+        if close_on_complete:
+            driver.close()
+
+    def __repr__(self):
+        return """
+{name}
+
+{about_us}
+
+Specialties: {specialties}
+
+Website: {website}
+Industry: {industry}
+Type: {company_type}
+Headquarters: {headquarters}
+Company Size: {company_size}
+Founded: {founded}
+
+Showcase Pages
+{showcase_pages}
+
+Affiliated Companies
+{affiliated_companies}
+    """.format(
+        name = self.name,
+        about_us = self.about_us,
+        specialties = self.specialties,
+        website= self.website,
+        industry= self.industry,
+        company_type= self.company_type,
+        headquarters= self.headquarters,
+        company_size= self.company_size,
+        founded= self.founded,
+        showcase_pages = self.showcase_pages,
+        affiliated_companies = self.affiliated_companies
+    )

usr/lib/python3.6/site-packages/linkedin_user_scraper/functions.py

@@ -0,0 +1,15 @@
+import re
+
+def time_divide(string):
+    duration = re.search("\((.*?)\)", string)
+
+    if duration != None:
+        duration = duration.group(0)
+        string = string.replace(duration, "").strip()
+    else:
+        duration = "()"
+
+    times = string.split("–")
+    return (times[0].strip(), times[1].strip(), duration[1:-1])
+
+

usr/lib/python3.6/site-packages/linkedin_user_scraper/objects.py

@@ -0,0 +1,51 @@
+
+class Institution(object):
+    institution_name = None
+    website = None
+    industry = None
+    type = None
+    headquarters = None
+    company_size = None
+    founded = None
+
+    def __init__(self, name=None, website=None, industry=None, type=None, headquarters=None, company_size=None, founded=None):
+        self.name = name
+        self.website = website
+        self.industry = industry
+        self.type = type
+        self.headquarters = headquarters
+        self.company_size = company_size
+        self.founded = founded
+
+class Experience(Institution):
+    from_date = None
+    to_date = None
+    description = None
+    position_title = None
+
+    def __init__(self, from_date = None, to_date = None, description = None, position_title = None):
+        self.from_date = from_date
+        self.to_date = to_date
+        self.description = description
+        self.position_title = position_title
+
+    def __repr__(self):
+        return "{position_title} at {company} from {from_date} to {to_date}".format( from_date = self.from_date, to_date = self.to_date, position_title = self.position_title, company = self.institution_name)
+
+
+class Education(Institution):
+    from_date = None
+    to_date = None
+    description = None
+    degree = None
+
+    def __init__(self, from_date = None, to_date = None, description = None, degree = None):
+        self.from_date = from_date
+        self.to_date = to_date
+        self.description = description
+        self.degree = degree
+
+    def __repr__(self):
+        return "{degree} at {company} from {from_date} to {to_date}".format( from_date = self.from_date, to_date = self.to_date, degree = self.degree, company = self.institution_name)
+
+

usr/lib/python3.6/site-packages/linkedin_user_scraper/person.py

@@ -0,0 +1,87 @@
+import requests
+from lxml import html
+from selenium import webdriver
+from .functions import time_divide
+import os
+
+class Person(object):
+    name = None
+    experiences = []
+    educations = []
+    also_viewed_urls = []
+    linkedin_url = None
+    driver = None
+
+    def __init__(self, linkedin_url = None, experiences = [], educations = [], driver = None, scrape = True):
+        self.linkedin_url = linkedin_url
+        self.experiences = experiences
+        self.educations = educations
+
+        if driver is None:
+            try:
+                if os.getenv("CHROMEDRIVER") == None:
+                    driver_path = os.path.join(os.path.dirname(__file__), 'drivers/chromedriver')
+                else:
+                    driver_path = os.getenv("CHROMEDRIVER")
+
+                driver = webdriver.Chrome(driver_path)
+            except:
+                driver = webdriver.Chrome()
+
+        driver.get(linkedin_url)
+        self.driver = driver
+
+        if scrape:
+            self.scrape()
+
+
+    def add_experience(self, experience):
+        self.experiences.append(experience)
+
+    def add_education(self, education):
+        self.educations.append(education)
+
+    def scrape(self, close_on_complete=True):
+        driver = self.driver
+        page = driver.get(self.linkedin_url)
+
+        # get name
+        self.name = driver.find_element_by_id("name").text
+
+        # get experience
+        exp = driver.find_element_by_id("experience")
+        for position in exp.find_elements_by_class_name("position"):
+            position_title = position.find_element_by_class_name("item-title").text
+            company = position.find_element_by_class_name("item-subtitle").text
+
+            try:
+                times = position.find_element_by_class_name("date-range").text
+                from_date, to_date, duration = time_divide(times)
+            except:
+                from_date, to_date = (None, None)
+            experience = Experience( position_title = position_title , from_date = from_date , to_date = to_date)
+            experience.institution_name = company
+            self.add_experience(experience)
+
+        # get education
+        edu = driver.find_element_by_id("education")
+        for school in edu.find_elements_by_class_name("school"):
+            university = school.find_element_by_class_name("item-title").text
+            degree = school.find_element_by_class_name("original").text
+            try:
+                times = school.find_element_by_class_name("date-range").text
+                from_date, to_date, duration = time_divide(times)
+            except:
+                from_date, to_date = (None, None)
+            education = Education(from_date = from_date, to_date = to_date, degree=degree)
+            education.institution_name = university
+            self.add_education(education)
+
+        # get 
+        if close_on_complete:
+            driver.close()
+
+    def __repr__(self):
+        return "{name}\n\nExperience\n{exp}\n\nEducation\n{edu}".format(name = self.name, exp = self.experiences, edu = self.educations)
+
+

usr/lib/python3.6/site-packages/linkedin_user_scraper/scraper.py

@@ -0,0 +1,8 @@
+#!/usr/bin/python3
+
+import requests
+from lxml import html
+from selenium import webdriver
+import re
+import os
+