Spaces:
Sleeping
Sleeping
File size: 3,493 Bytes
36c3f07 0ebd299 36c3f07 0ebd299 36c3f07 0ebd299 36c3f07 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 | from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from gradio_client import Client
import json
import gradio as gr
from webdriver_manager.chrome import ChromeDriverManager
def scrape_data(amazon_url):
service = Service(ChromeDriverManager().install())
options = Options()
options.add_argument("--headless")
driver = webdriver.Chrome(service=service, options=options)
driver.get(amazon_url)
amazon_title_element = WebDriverWait(driver, 5).until(
EC.presence_of_element_located((By.ID, 'productTitle'))
)
amazon_title = amazon_title_element.text.strip()
amazon_desc_element = driver.find_element(By.ID, 'feature-bullets')
amazon_desc = amazon_desc_element.text.strip()
driver.get(f'https://www.flipkart.com/search?q={"+".join(amazon_title.split()[:6])}')
flipkart_url = ''
elements = driver.find_elements(By.CLASS_NAME, '_2rpwqI')
for element in elements:
text_content = element.get_attribute('href')
if amazon_title.split()[0].lower() in text_content:
flipkart_url = text_content
break
if not flipkart_url:
elements = driver.find_elements(By.CLASS_NAME, '_1fQZEK')
for element in elements:
text_content = element.get_attribute('href')
if amazon_title.split()[0].lower() in text_content:
flipkart_url = text_content
break
if(flipkart_url.find('flipkart.com') == -1):
flipkart_url = 'https://www.flipkart.com' + flipkart_url
driver.get(flipkart_url)
final_elements = driver.find_elements(By.CLASS_NAME, '_2418kt')
flipkart_desc = ''
for element in final_elements:
flipkart_desc = element.text
driver.quit()
return amazon_desc, flipkart_desc
def compare_descriptions(amazon_url):
client = Client("https://atulit23-google-flan-t5.hf.space/")
print(amazon_url)
amazon_desc, flipkart_desc = scrape_data(amazon_url)
description_to_compare = "First description: " + amazon_desc + " " + "Second Description: " + flipkart_desc + " As you can see I have provided you with two descriptions. Compare these two descriptions to see if for the same field some different information has been provided. Answer in yes or no."
print(description_to_compare)
result = client.predict(
description_to_compare,
api_name="/predict"
)
final_result = {"Amazon": amazon_desc, "Flipkart": flipkart_desc, "result": ""}
if result.find("yes") != -1:
final_result["result"] = "Mismatch Detected between the descriptions at Amazon & Flipkart."
else:
final_result["result"] = "No Mismatch Detected between the descriptions at Amazon & Flipkart."
return json.dumps(final_result)
inputs_image_url = [
gr.Textbox(type="text", label="Topic Name"),
]
outputs_result_dict = [
gr.Textbox(type="text", label="Result"),
]
interface_image_url = gr.Interface(
fn=compare_descriptions,
inputs=inputs_image_url,
outputs=outputs_result_dict,
title="Text Generation",
cache_examples=False,
)
gr.TabbedInterface(
[interface_image_url],
tab_names=['Some inference']
).launch() |