The following code was answered by a user, here is original post
-https://stackoverflow.com/questions/64917833/print-output-in-as-a-list
The output looks correct and all
however they exported as a ipynb file. Im sure this can be exported as a csv.
What code can be added so i can run this in python and export to csv?
from openpyxl import load_workbook
import time
import pandas as pd
import numpy as np
from selenium import webdriver
from bs4 import BeautifulSoup
import requests
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from webdriver_manager.chrome import ChromeDriverManager
test1=[]
options = Options()
driver = webdriver.Chrome(ChromeDriverManager().install())
url = "https://www.linkedin.com/uas/login?session_redirect=https%3A%2F%2Fwww%2Elinkedin%2Ecom%2Fsearch%2Fresults%2Fpeople%2F%3FcurrentCompany%3D%255B%25221252860%2522%255D%26geoUrn%3D%255B%2522103644278%2522%255D%26keywords%3Dsales%26origin%3DFACETED_SEARCH%26page%3D2&fromSignIn=true&trk=cold_join_sign_in"
driver.get(url)
time.sleep(2)
username = driver.find_element_by_id('username')
username.send_keys('kbradons04@gmail.com')
password = driver.find_element_by_id('password')
password.send_keys('Applesauce1')
password.submit()
driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
time.sleep(3)
elementj=(WebDriverWait(driver,10).until(EC.visibility_of_all_elements_located((By.CSS_SELECTOR,".subline-level-2.t-12.t-black--light.t-normal.search-result__truncate"))))
place1=[j.text for j in elementj]
elementk=WebDriverWait(driver,10).until(EC.visibility_of_all_elements_located((By.CSS_SELECTOR,".subline-level-1.t-14.t-black.t-normal.search-result__truncate")))
compan=[c.text for c in elementk]
element1 = driver.find_elements_by_class_name("actor-name")
title=[t.text for t in element1]
diction={"Location":place1,"Company":compan,"Title":title}
test1.append(diction)
print(test1)
df = pd.DataFrame(test1)
def explode(df, lst_cols, fill_value=''):
# make sure `lst_cols` is a list
if lst_cols and not isinstance(lst_cols, list):
lst_cols = [lst_cols]
# all columns except `lst_cols`
idx_cols = df.columns.difference(lst_cols)
# calculate lengths of lists
lens = df[lst_cols[0]].str.len()
if (lens > 0).all():
# ALL lists in cells aren't empty
return pd.DataFrame({
col:np.repeat(df[col].values, df[lst_cols[0]].str.len())
for col in idx_cols
}).assign(**{col:np.concatenate(df[col].values) for col in lst_cols}) \
.loc[:, df.columns]
else:
# at least one list in cells is empty
return pd.DataFrame({
col:np.repeat(df[col].values, df[lst_cols[0]].str.len())
for col in idx_cols
}).assign(**{col:np.concatenate(df[col].values) for col in lst_cols}) \
.append(df.loc[lens==0, idx_cols]).fillna(fill_value) \
.loc[:, df.columns]
explode(df,['Location','Company','Title'])
