hf-similarity-check / search_engine.py
Mitul Mohammad Abdullah Al Mukit
updates
e029c8d
raw
history blame
4.85 kB
import base64
import os
import rsa
from datetime import date
import secrets
import string
import requests
import json
from dotenv import load_dotenv
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
import time
from bs4 import BeautifulSoup
import csv
def generate_token_id(length):
characters = string.ascii_letters + string.digits # + string.punctuation
token = ''.join(secrets.choice(characters) for _ in range(length))
return token
# Examples for what will be generated
# 5!bA9H2f1q^...
# Xe7uM$4d9@...
# &3yTb1*8Z#...
# %pWqN7!6zX...
# @9oV!s6Rd2...
def get_today_date():
today = date.today()
return str(today)
# Example for what will be returned
# 2023-06-29
def get_request(get_url, params):
# get_url = 'http://ipygg-api-test-env.ap-east-1.elasticbeanstalk.com/SBT'
pubkey_path = os.path.join(os.path.dirname(__file__), '..', 'pubkey.pem')
with open(pubkey_path, 'rb') as f:
pubKey = rsa.PublicKey.load_pkcs1(f.read())
for key, value in params.items():
value_bytes = value.encode("utf-8")
encrypted_value = rsa.encrypt(value_bytes, pubKey)
encoded_value = base64.b64encode(encrypted_value)
params[key] = encoded_value
# Write the encrypted and encoded values to a file
with open("sbt_request.txt", "w") as f:
for key, value in params.items():
f.write(f"{key}: {value}\n\n")
# posting Json file to api
r = requests.get(get_url, params=params)# extracting data in json format
data = r.json()
print(f'get request: {data}')
def post_request(post_url, data):
# post_url = 'http://ipygg-api-test-env.ap-east-1.elasticbeanstalk.com/SBT'
pubkey_path = os.path.join(os.path.dirname(__file__), '..', 'pubkey.pem')
with open(pubkey_path, 'rb') as f:
pubKey = rsa.PublicKey.load_pkcs1(f.read())
for key, value in data.items():
value_bytes = value.encode("utf-8")
encrypted_value = rsa.encrypt(value_bytes, pubKey)
encoded_value = base64.b64encode(encrypted_value)
data[key] = encoded_value
# Write the encrypted and encoded values to a file
with open("sbt_request.txt", "w") as f:
for key, value in data.items():
f.write(f"{key}: {value}\n\n")
# posting Json file to api
r = requests.post(post_url, data=data)
print(f'post request: {r.json}')
def search_on_engine(search_data):
# clearing csv file data
csv_filename = "search_result.csv"
f = open(csv_filename, "w+") # opening the file with w+ mode truncates the file
# writer.writeheader()
f.close()
# set up driver
driver = webdriver.Chrome()
load_dotenv()
search_url = os.environ.get("search-engine-url")
driver.get(search_url)
# assert "Python" in driver.title
for search_tag_key in search_data:
search_tag = search_data[search_tag_key]
# Searching search tag in query
elem = driver.find_element(By.NAME, "query")
elem.clear()
elem.send_keys(search_tag)
submit_elem = driver.find_element(By.ID, "submit")
submit_elem.click()
time.sleep(8) # delay for 10 seconds: 2 seconds for Yahoo! search, 6 seconds for Google search
assert "No results found." not in driver.page_source
# extract link from page
html = driver.page_source # search url remains the same after searching
# time.sleep(10) # delay for 10 seconds: 2 seconds for Yahoo! search, 6 seconds for Google search
soup = BeautifulSoup(html, 'html.parser')
result_links = []
for link in soup.find_all('a'):
result_links.append(link.get('href'))
# print(link.get('href'))
# store in csv
result_dict = {
"tag": search_tag,
"results": result_links
}
with open(csv_filename, 'a', encoding='UTF8', newline='') as f:
# writer = csv.writer(f)
writer = csv.DictWriter(f, fieldnames=["tag","results"])
writer.writerow(result_dict)
# save the link to db
# post_request("post_url", result_link)
def get_data_link(chinese_name, english_name, address):
# get phone number from db
# phone_no = get_request(get_url, english_name)
phone_no = '12345678'
# create data set
search_data = {
"chi_name": chinese_name,
"eng_name": english_name,
"address": address,
"phone_number": phone_no
}
# pass data to search engine
result_link = search_on_engine(search_data)
# show the link
# return result_link
# get_data_link('劉柏政','Lau, Pak Ching','FLT 1939 18/F KM WAN HSE, CHOIHUNG EST 1 HUNG MUI AVENUE, NGAU CHI WAN KLN')
# search_on_engine('Lau, Pak Ching')