More documentation for how to use with requests/lxml

[lukeprofits]

Selenium is awesome, but I am trying to use this with requests and lxml. It seems like it is solving things properly, but I am having trouble submitting the solution. Could you add some example usage to the readme?

This is what I am doing right now using requests/lxml:

import random
import requests
from lxml import html
from fake_useragent import UserAgent
import csv
import time
import os
from amazoncaptcha import AmazonCaptcha


amazon_captcha_xpath = '//h4[contains(text(), "Enter the characters you see below")]'
captcha_image_xpath = '//div[@class="a-row a-text-center"]/img/@src'


def get_link(url, session=None, user_agent=None, proxy=None):
    """
    Fetches the HTML content from the provided URL.
    Returns a parsed lxml HTML tree that can be used with XPath.
    """
    ua = UserAgent()
    headers = {'User-Agent': ua.google if not user_agent else user_agent}
    proxies = {'http': proxy, 'https': proxy} if proxy else {}

    if session is None:
        session = requests.Session()

    response = session.get(url, headers=headers, proxies=proxies)
    tree = html.fromstring(response.content)

    return tree, session


# code that does stuff assuming there is no captcha. Leaving it out because it's long and probably not helpful.

if tree.xpath(amazon_captcha_xpath):
    bot_check = True
    print(html.tostring(tree).decode())
    print('[ Captcha Detected! ]')

    captcha_image_link = tree.xpath(captcha_image_xpath)[0]
    print(captcha_image_link)

    solution = AmazonCaptcha.fromlink(captcha_image_link).solve()
    print(f'Solution is: {solution}')

    print('Pausing to seem human...')
    time.sleep(random.randrange(3, 15))

 
    print('Submitting solution')
    
    # THIS IS THE PART TO SUBIMT IT THAT DOES NOT SEEM TO WORK
    
    amzn = tree.xpath('//input[@name="amzn"]/@value')[0]
    amzn_r = tree.xpath('//input[@name="amzn-r"]/@value')[0]

    data = {
        'amzn': amzn,
        'amzn-r': amzn_r,
        'field-keywords': solution
    }

    response = response = session.post('https://www.amazon.com/errors/validateCaptcha', data=data)

    # check response
    print(response.status_code)   # always comes back as 503
    #print(response.text)
    #input('PAUSED')
    ```

[3ldar]

It is not in python but I will share my nodejs implementation of how to resolve amazon captcha:

 const amzn = $("form input[type=hidden]").val();
 let amazonPass: string;
    if (options.baseUrl.includes('?')) {
        const [base, query] = options.baseUrl.split('?');

        amazonPass = `${base}/errors/validateCaptcha?amzn=${amzn}&amzn-r=/&field-keywords=${captcha}&${query}`
    } else {
        amazonPass = `${options.baseUrl}/errors/validateCaptcha?amzn=${amzn}&amzn-r=/&field-keywords=${captcha}`
    }

    const response =  await gotScraping({
        url: amazonPass,
        cookieJar: options.cookieJar,
        followRedirect: true,
        headers: {
            "referer": options.baseUrl
        },
        // @ts-ignore
        proxyUrl: options.proxyUrl,
        sessionToken: options.sessionToken,
        throwHttpErrors: false,

    })

gotScraping is a request like a library. The thing it is a get request, requires referer and and a followup URL to redirect after the captcha resolves.

[stale]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.