Active_prgs/Redgrave/vCardSearchAndDownload.py

"""

vCardSearchAndDownload

Created by:
Emanuel Borges
12.30.2024

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.

"""

import os
import time
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from urllib.parse import urljoin
import requests
import urllib


#BASE_URL = "https://perkinscoie.com/people-search"
#BASE_URL = "https://www.klgates.com/people"
BASE_URL = "https://www.hoganlovells.com/en/our-people"

VCARD_DIR = "vcards"
os.makedirs(VCARD_DIR, exist_ok = True)


driver = webdriver.Chrome()

version = '0.3.0'


def search_and_download_vcards(person_name, element_id_name, quotedSearch = False, protectedDownload = False):
    try:
        driver.get(BASE_URL)

        time.sleep(3)


        search_box = driver.find_element(By.ID, element_id_name)
        #search_box = driver.find_element(By.ID, "searchbox")
        #search_box = driver.find_element(By.ID, "edit-keyword")
        #search_box = driver.find_element(By.ID, "name3")
        search_box.clear()
        if quotedSearch == True:
            search_box.send_keys(f'"{person_name}"')
        else:
            search_box.send_keys(person_name)
        
        search_box.send_keys(Keys.RETURN)

        time.sleep(3)


        results = driver.find_elements(By.CSS_SELECTOR, "a[href*='vcard']")
        
        if not results:
            print(f"No vCards found for '{person_name}'.")
            return


        for link in results:
            vcard_url = link.get_attribute("href")
            if protectedDownload == True:
                download_vcard_protected(vcard_url,person_name)
            else:
                download_vcard(vcard_url,person_name)

    except Exception as e:
        print(f"Error during search or download: {e}")
##    finally:
##        driver.quit()


def download_vcard(vcard_url, person_name):
    try:
        response = requests.get(vcard_url)
        response.raise_for_status()

        #filename = os.path.basename(vcard_url)
        filename = f"{person_name}.vcf"
        filepath = os.path.join(VCARD_DIR,filename)


        with open(filepath,"wb") as file:
            file.write(response.content)
        print(f"Downloaded vCard: {filepath}")
    except Exception as e:
        print(f"Error downloading vCard from {vcard_url}: {e}")


def download_vcard_protected(vcard_url, person_name):
    try:
        req = urllib.request.Request(vcard_url)
        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')
        r = urllib.request.urlopen(req).read()#.decode('utf-8')
    
        filename = f"{person_name}.vcf"
        filepath = os.path.join(VCARD_DIR,filename)


        with open(filepath,"wb") as file:
            file.write(r)
        
        print(f"Downloaded vCard: {filepath}")
    except Exception as e:
        print(f"Error downloading vCard from {vcard_url}: {e}")

if __name__ == '__main__':
    #inputFilePath = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\MAL-NamesToFind\KLGATES.txt"
    #inputFilePath = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\MAL-NamesToFind\KLGATES_SUB3.txt"
    #inputFilePath = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\MAL-NamesToFind\TEST.txt"
    inputFilePath = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\MAL-NamesToFind\HOGANLOVELLS_SUB1.txt"

    element_id_name = "name3"


    ##  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
    listOfEmailAddresses = set()


    contents = open(inputFilePath).readlines()
    for line in contents:
        line = line.replace("\n","")
        uniqueRowNumb,emailAddr = line.split("|")
        person_to_search = emailAddr
        search_and_download_vcards(person_to_search, element_id_name, protectedDownload = True)


    #person_to_search = "Gaia Bacchi"
    #person_to_search = "tim.weston@klgates.com"
    #person_to_search = "BPeters@perkinscoie.com"
    #person_to_search = "Katie.McMullan@hoganlovells.com"
    #search_and_download_vcards(person_to_search, element_id_name, protectedDownload = True)

    driver.quit()
Revision:	875
Committed:	Tue Dec 31 03:27:12 2024 UTC (14 months, 3 weeks ago) by nino.borges
Content type:	text/x-python
File size:	4550 byte(s)
Log Message:	I started getting forbidden messages when trying to download some vcards from other sites, so I added support for urllib, which does a bit better of a job with dealing with sending header information. I also broke out a few variables, so I can better support other element texts, etc. Works great for Hogan Lovells now too.
#	User	Rev	Content
1	nino.borges	873	"""
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	nino.borges	875	import urllib
21	nino.borges	873
22
23	nino.borges	874	#BASE_URL = "https://perkinscoie.com/people-search"
24	nino.borges	875	#BASE_URL = "https://www.klgates.com/people"
25			BASE_URL = "https://www.hoganlovells.com/en/our-people"
26	nino.borges	873
27			VCARD_DIR = "vcards"
28			os.makedirs(VCARD_DIR, exist_ok = True)
29
30
31			driver = webdriver.Chrome()
32
33	nino.borges	875	version = '0.3.0'
34	nino.borges	873
35
36	nino.borges	875	def search_and_download_vcards(person_name, element_id_name, quotedSearch = False, protectedDownload = False):
37	nino.borges	873	try:
38			driver.get(BASE_URL)
39
40			time.sleep(3)
41
42
43	nino.borges	875	search_box = driver.find_element(By.ID, element_id_name)
44			#search_box = driver.find_element(By.ID, "searchbox")
45	nino.borges	874	#search_box = driver.find_element(By.ID, "edit-keyword")
46			#search_box = driver.find_element(By.ID, "name3")
47	nino.borges	873	search_box.clear()
48	nino.borges	875	if quotedSearch == True:
49			search_box.send_keys(f'"{person_name}"')
50			else:
51			search_box.send_keys(person_name)
52
53	nino.borges	873	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	nino.borges	874
60	nino.borges	873	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	nino.borges	875	if protectedDownload == True:
68			download_vcard_protected(vcard_url,person_name)
69			else:
70			download_vcard(vcard_url,person_name)
71	nino.borges	873
72			except Exception as e:
73			print(f"Error during search or download: {e}")
74	nino.borges	874	## finally:
75			## driver.quit()
76	nino.borges	873
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	nino.borges	875	def download_vcard_protected(vcard_url, person_name):
97			try:
98			req = urllib.request.Request(vcard_url)
99			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')
100			r = urllib.request.urlopen(req).read()#.decode('utf-8')
101
102			filename = f"{person_name}.vcf"
103			filepath = os.path.join(VCARD_DIR,filename)
104
105
106			with open(filepath,"wb") as file:
107			file.write(r)
108
109			print(f"Downloaded vCard: {filepath}")
110			except Exception as e:
111			print(f"Error downloading vCard from {vcard_url}: {e}")
112
113	nino.borges	873	if __name__ == '__main__':
114	nino.borges	874	#inputFilePath = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\MAL-NamesToFind\KLGATES.txt"
115	nino.borges	875	#inputFilePath = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\MAL-NamesToFind\KLGATES_SUB3.txt"
116	nino.borges	874	#inputFilePath = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\MAL-NamesToFind\TEST.txt"
117	nino.borges	875	inputFilePath = r"C:\Users\eborges\OneDrive - Redgrave LLP\Documents\Cases\Amazon\MAL-NamesToFind\HOGANLOVELLS_SUB1.txt"
118	nino.borges	873
119	nino.borges	875	element_id_name = "name3"
120	nino.borges	874
121
122	nino.borges	875
123	nino.borges	874	## 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
124			listOfEmailAddresses = set()
125
126
127			contents = open(inputFilePath).readlines()
128			for line in contents:
129			line = line.replace("\n","")
130			uniqueRowNumb,emailAddr = line.split("\|")
131			person_to_search = emailAddr
132	nino.borges	875	search_and_download_vcards(person_to_search, element_id_name, protectedDownload = True)
133	nino.borges	874
134
135	nino.borges	873
136	nino.borges	874
137	nino.borges	873	#person_to_search = "Gaia Bacchi"
138			#person_to_search = "tim.weston@klgates.com"
139	nino.borges	874	#person_to_search = "BPeters@perkinscoie.com"
140			#person_to_search = "Katie.McMullan@hoganlovells.com"
141	nino.borges	875	#search_and_download_vcards(person_to_search, element_id_name, protectedDownload = True)
142	nino.borges	874
143			driver.quit()