File size: 4,376 Bytes
edaef93 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 |
import requests
from bs4 import BeautifulSoup
from openai import OpenAI
import base64
from config import openai_api
def encode_image(image_path):
with open(image_path, "rb") as image_file:
return base64.b64encode(image_file.read()).decode('utf-8')
def get_page_content(url):
# Send a GET request to the page
response = requests.get(url)
# Parse the HTML content using BeautifulSoup
soup = BeautifulSoup(response.content, "html.parser")
url_detailed = soup.find("a", {"data-testid":"ux-call-to-action"})["href"]
url_detailed
try:
# Send a GET request to the page
response = requests.get(url_detailed)
# Parse the HTML content using BeautifulSoup
soup = BeautifulSoup(response.content, "html.parser")
# Extract the product description
product_details_div = soup.find("div", {"class":"tabs__cell"})
product_details_div.get_text()
except:
# Send a GET request to the page
response = requests.get(url)
# Parse the HTML content using BeautifulSoup
soup = BeautifulSoup(response.content, "html.parser")
# Extract the product description
product_details_div = soup.find("div", {"class":"tabs__cell"})
title = soup.find("h1", {"class" : "x-item-title__mainTitle"})
title.get_text()
# description = {product_details_div.get_text("\n")}"
description = f"### TITLE : {title.get_text()} \n"
for div in product_details_div.find_all("div"):
description += div.get_text("\n")
try:
img_part = soup.find("div", {"class":"ux-image-grid no-scrollbar"})
imgs = []
for img in img_part.find_all("img"):
imgs.append(img["src"])
# Print the results
# print(f"Description: {description}")
# print(f"Image URLs: {imgs}")
except:
img_part = soup.find("div", {"class":"ux-image-carousel-item"})
imgs.append(img_part.find_all("img")[0]["src"])
pass
return description, imgs
client = OpenAI(api_key=openai_api)
def get_ai_response(prompt_content, additional_information= ""):
response = client.chat.completions.create(
model="gpt-4o",
messages=[
{
"role": "system",
"content": [
{
"type": "text",
"text": f"You will be given ebay listings. Your task is to say if there is anything forbidden by their policies or illegal within the legal framework (former court decisions etc). You specify the legal basis, justify thoroughly, and cite all necessary regulations that are relevant and in the scope of application for this type of product in the corresponding region. Your focus should be on preventing any illegal listing or doing. {additional_information}\n\nYou format your answers like this:\n\n# Compliance: Yes/No\n\n# Justification:\n"
}
]
},
{
"role": "user",
"content": prompt_content
},
],
temperature=1,
max_tokens=1439,
top_p=1,
frequency_penalty=0,
presence_penalty=0,
stream=True
)
return response
def get_answer(url, additional_information = ""):
description, imgs = get_page_content(url)
img_paths = []
for image_url in imgs:
filename = image_url.split("images/")[1].replace("/", "_")
response = requests.get(image_url, stream=True)
if response.status_code == 200:
with open(filename, "wb") as f:
for chunk in response.iter_content(1024):
f.write(chunk)
# print(f"Downloaded {filename}")
img_paths.append(filename)
else:
print(f"Failed to download {image_url}")
# img_path = img_paths[0]
# base64_image = encode_image(img_path)
prompt_content = []
for img_path in img_paths:
b64_img = encode_image(img_path)
dict_img = {
"type": "image_url",
"image_url": {
"url": f"data:image/jpeg;base64,{b64_img}",
}
}
prompt_content.append(dict_img)
prompt_content.append({
"type": "text",
"text": description
})
answer = get_ai_response(prompt_content, additional_information)
# answer = ""
return answer, description, imgs |