scrapinghub / portia

Visual scraping for Scrapy
BSD 3-Clause "New" or "Revised" License
9.22k stars 1.41k forks source link

Need Help scraping API #925

Open TwangyMoney opened 10 months ago

TwangyMoney commented 10 months ago

Can someone help me with this I'm having trouble. It feels really complex for me to understand how this works. This is basically what I'm trying to do: async def generate_response(instructions, history=None): if history is None: data = { "model": "gpt-3.5-turbo-16k-0613", "temperature": 0.75, "messages": [ {"role": "system", "content": instructions}, ], } else: data = { "model": "gpt-3.5-turbo-16k-0613", "temperature": 0.75, "messages": [ {"role": "system", "content": instructions}, *history, ], }

endpoint = "https://gpt4.xunika.uk/api/openai/v1/chat/completions"

headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer ak-wwwchatgptorguk",
}

try:
    async with aiohttp.ClientSession() as session:
        async with session.post(endpoint, headers=headers, json=data) as response:
            response_data = await response.json()
            print(f"response_data: {response.status}")
            choices = response_data["choices"]
            if choices:
                return choices[0]["message"]["content"]
except aiohttp.ClientError as error:
    print("Error making the request:", error)

  How can I implement portia here so it bypasses CloudFlare and gives me my response?
gabriel-batistuta commented 3 weeks ago

It seems that this project is no longer being maintained, OpenAI is making it difficult to use free APIs, so I recommend you check out this other, more active repository to solve your problem: https://github.com/PawanOsman/ChatGPT