| 1 |
"""
|
| 2 |
|
| 3 |
vCardSearchAndDownload
|
| 4 |
|
| 5 |
Created by:
|
| 6 |
Emanuel Borges
|
| 7 |
12.30.2024
|
| 8 |
|
| 9 |
This program uses chromedriver to first search for a person on a public company people search and then, if found, download the vCard for that person.
|
| 10 |
|
| 11 |
"""
|
| 12 |
|
| 13 |
import os
|
| 14 |
import time
|
| 15 |
from selenium import webdriver
|
| 16 |
from selenium.webdriver.common.by import By
|
| 17 |
from selenium.webdriver.common.keys import Keys
|
| 18 |
from urllib.parse import urljoin
|
| 19 |
import requests
|
| 20 |
import urllib
|
| 21 |
|
| 22 |
|
| 23 |
#BASE_URL = "https://perkinscoie.com/people-search"
|
| 24 |
#BASE_URL = "https://www.klgates.com/people"
|
| 25 |
BASE_URL = "https://www.hoganlovells.com/en/our-people"
|
| 26 |
|
| 27 |
VCARD_DIR = "vcards"
|
| 28 |
os.makedirs(VCARD_DIR, exist_ok = True)
|
| 29 |
|
| 30 |
|
| 31 |
driver = webdriver.Chrome()
|
| 32 |
|
| 33 |
version = '0.3.0'
|
| 34 |
|
| 35 |
|
| 36 |
def search_and_download_vcards(person_name, element_id_name, quotedSearch = False, protectedDownload = False):
|
| 37 |
try:
|
| 38 |
driver.get(BASE_URL)
|
| 39 |
|
| 40 |
time.sleep(3)
|
| 41 |
|
| 42 |
|
| 43 |
search_box = driver.find_element(By.ID, element_id_name)
|
| 44 |
#search_box = driver.find_element(By.ID, "searchbox")
|
| 45 |
#search_box = driver.find_element(By.ID, "edit-keyword")
|
| 46 |
#search_box = driver.find_element(By.ID, "name3")
|
| 47 |
search_box.clear()
|
| 48 |
if quotedSearch == True:
|
| 49 |
search_box.send_keys(f'"{person_name}"')
|
| 50 |
else:
|
| 51 |
search_box.send_keys(person_name)
|
| 52 |
|
| 53 |
search_box.send_keys(Keys.RETURN)
|
| 54 |
|
| 55 |
time.sleep(3)
|
| 56 |
|
| 57 |
|
| 58 |
results = driver.find_elements(By.CSS_SELECTOR, "a[href*='vcard']")
|
| 59 |
|
| 60 |
if not results:
|
| 61 |
print(f"No vCards found for '{person_name}'.")
|
| 62 |
return
|
| 63 |
|
| 64 |
|
| 65 |
for link in results:
|
| 66 |
vcard_url = link.get_attribute("href")
|
| 67 |
if protectedDownload == True:
|
| 68 |
download_vcard_protected(vcard_url,person_name)
|
| 69 |
else:
|
| 70 |
download_vcard(vcard_url,person_name)
|
| 71 |
|
| 72 |
except Exception as e:
|
| 73 |
print(f"Error during search or download: {e}")
|
| 74 |
## finally:
|
| 75 |
## driver.quit()
|
| 76 |
|
| 77 |
|
| 78 |
|
| 79 |
def download_vcard(vcard_url, person_name):
|
| 80 |
try:
|
| 81 |
response = requests.get(vcard_url)
|
| 82 |
response.raise_for_status()
|
| 83 |
|
| 84 |
#filename = os.path.basename(vcard_url)
|
| 85 |
filename = f"{person_name}.vcf"
|
| 86 |
filepath = os.path.join(VCARD_DIR,filename)
|
| 87 |
|
| 88 |
|
| 89 |
with open(filepath,"wb") as file:
|
| 90 |
file.write(response.content)
|
| 91 |
print(f"Downloaded vCard: {filepath}")
|
| 92 |
except Exception as e:
|
| 93 |
print(f"Error downloading vCard from {vcard_url}: {e}")
|
| 94 |
|
| 95 |
|
| 96 |
def download_vcard_protected(vcard_url, person_name):
|
| 97 |
"""Some sites are giving me a forbidden message, so making this second function that will use urllib instead of requests"""
|
| 98 |
try:
|
| 99 |
req = urllib.request.Request(vcard_url)
|
| 100 |
req.add_header('user-agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36')
|
| 101 |
r = urllib.request.urlopen(req).read()#.decode('utf-8')
|
| 102 |
|
| 103 |
filename = f"{person_name}.vcf"
|
| 104 |
filepath = os.path.join(VCARD_DIR,filename)
|
| 105 |
|
| 106 |
|
| 107 |
with open(filepath,"wb") as file:
|
| 108 |
file.write(r)
|
| 109 |
|
| 110 |
print(f"Downloaded vCard: {filepath}")
|
| 111 |
except Exception as e:
|
| 112 |
print(f"Error downloading vCard from {vcard_url}: {e}")
|
| 113 |
|
| 114 |
if __name__ == '__main__':
|
| 115 |
#inputFilePath = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\MAL-NamesToFind\KLGATES.txt"
|
| 116 |
#inputFilePath = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\MAL-NamesToFind\KLGATES_SUB3.txt"
|
| 117 |
#inputFilePath = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\MAL-NamesToFind\TEST.txt"
|
| 118 |
inputFilePath = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\MAL-NamesToFind\HOGANLOVELLS_SUB4.txt"
|
| 119 |
|
| 120 |
element_id_name = "name3"
|
| 121 |
|
| 122 |
|
| 123 |
|
| 124 |
## This can be a list of any value to search on but for now I need it to be unique, which is why I'm searching only on email addresses
|
| 125 |
listOfEmailAddresses = set()
|
| 126 |
|
| 127 |
|
| 128 |
contents = open(inputFilePath).readlines()
|
| 129 |
for line in contents:
|
| 130 |
line = line.replace("\n","")
|
| 131 |
uniqueRowNumb,emailAddr = line.split("|")
|
| 132 |
person_to_search = emailAddr
|
| 133 |
search_and_download_vcards(person_to_search, element_id_name, protectedDownload = True)
|
| 134 |
|
| 135 |
|
| 136 |
|
| 137 |
|
| 138 |
#person_to_search = "Gaia Bacchi"
|
| 139 |
#person_to_search = "tim.weston@klgates.com"
|
| 140 |
#person_to_search = "BPeters@perkinscoie.com"
|
| 141 |
#person_to_search = "Katie.McMullan@hoganlovells.com"
|
| 142 |
#search_and_download_vcards(person_to_search, element_id_name, protectedDownload = True)
|
| 143 |
|
| 144 |
driver.quit()
|
