如何在异步 Python 中用 CapSkip 识别 Pydoll 验证码

# Windows PowerShell, in an empty folder
python -m venv .venv
.\.venv\Scripts\python.exe -m pip install pydoll-python capskip

# pip install pydoll-python capskip
import asyncio

from pydoll import Chrome
from pydoll.browser.options import ChromiumOptions

PAGE = 'https://example.com/page-with-recaptcha'


async def main():
    options = ChromiumOptions()
    options.headless = True  # set to False to watch the window
    async with Chrome(options=options) as browser:
        tab = await browser.start()
        await tab.go_to(PAGE)
        print(await tab.title())


asyncio.run(main())

# pip install capskip
import asyncio

from capskip import AsyncCapSkip


async def main():
    solver = AsyncCapSkip(host='127.0.0.1', port=8080)
    result = await solver.recaptcha(
        sitekey='YOUR_SITEKEY',
        url='https://example.com/page-with-recaptcha',
    )
    print(result['code'][:30])


asyncio.run(main())

from urllib.parse import parse_qs, urlparse


async def find_sitekey(tab):
    # A normal widget carries data-sitekey. A widget drawn by
    # grecaptcha.render() only leaves its iframe, with k=<sitekey>.
    found = await tab.query(
        '.g-recaptcha[data-sitekey], '
        'iframe[src*="recaptcha/api2/anchor"]',
        timeout=10,
    )
    if found.tag_name == 'iframe':
        src = found.get_attribute('src')
        return parse_qs(urlparse(src).query)['k'][0]
    return found.get_attribute('data-sitekey')

from capskip import AsyncCapSkip

solver = AsyncCapSkip(host='127.0.0.1', port=8080)


async def solve(sitekey, url):
    result = await solver.recaptcha(sitekey, url)
    return result['code']

import json

FILL_JS = """
(function (token) {
  var seen = new Set(), fn = null;
  document.querySelectorAll('textarea[name="g-recaptcha-response"]')
    .forEach(function (box) { box.value = token; });
  (function walk(o, depth) {
    if (!o || typeof o !== 'object' || seen.has(o) || depth > 6) return;
    seen.add(o);
    for (var k in o) {
      var v; try { v = o[k]; } catch (e) { continue; }
      if (k === 'callback' && !fn) {
        fn = typeof v === 'string' ? window[v] : v;
      }
      if (v && typeof v === 'object' && !(v instanceof Node)) {
        walk(v, depth + 1);
      }
    }
  })(window.___grecaptcha_cfg, 0);
  if (typeof fn === 'function') fn(token);
  return typeof fn === 'function';
})(%s)
"""


async def fill_token(tab, token):
    reply = await tab.execute_script(
        FILL_JS % json.dumps(token), return_by_value=True)
    outcome = reply['result']
    if 'exceptionDetails' in outcome:
        error = outcome['exceptionDetails']['exception']
        raise RuntimeError(error['description'])
    return outcome['result']['value']  # True if a callback ran

async def main():
    options = ChromiumOptions()
    options.headless = True  # set to False to watch the window
    async with Chrome(options=options) as browser:
        tab = await browser.start()
        await tab.go_to(PAGE)
        sitekey = await find_sitekey(tab)
        token = await solve(sitekey, await tab.current_url())
        if not await fill_token(tab, token):
            button = await tab.query('form button[type="submit"]')
            async with tab.expect_navigation():
                await button.click()
        print(await tab.title())


asyncio.run(main())

async def main():
    options = ChromiumOptions()
    options.headless = True  # set to False to watch the window
    async with Chrome(options=options) as browser:
        tab = await browser.start()
        await tab.go_to(PAGE)
        sitekey = await find_sitekey(tab)
        token = await solve(sitekey, await tab.current_url())
        if await fill_token(tab, token):
            # The page's own callback takes over. What it does next is
            # page specific: this page writes its answer into #result.
            await tab.wait_for_script(
                "var r = document.querySelector('#result');"
                "return r && r.textContent !== 'waiting';"
            )
        print(await (await tab.query('#result')).text())


asyncio.run(main())

# pip install pydoll-python capskip
import asyncio
import json
from urllib.parse import parse_qs, urlparse

from capskip import AsyncCapSkip
from pydoll import Chrome
from pydoll.browser.options import ChromiumOptions

PAGE = 'https://example.com/page-with-recaptcha'

solver = AsyncCapSkip(host='127.0.0.1', port=8080)

# Put the token in every response box, then run the page's callback.
FILL_JS = """
(function (token) {
  var seen = new Set(), fn = null;
  document.querySelectorAll('textarea[name="g-recaptcha-response"]')
    .forEach(function (box) { box.value = token; });
  (function walk(o, depth) {
    if (!o || typeof o !== 'object' || seen.has(o) || depth > 6) return;
    seen.add(o);
    for (var k in o) {
      var v; try { v = o[k]; } catch (e) { continue; }
      if (k === 'callback' && !fn) {
        fn = typeof v === 'string' ? window[v] : v;
      }
      if (v && typeof v === 'object' && !(v instanceof Node)) {
        walk(v, depth + 1);
      }
    }
  })(window.___grecaptcha_cfg, 0);
  if (typeof fn === 'function') fn(token);
  return typeof fn === 'function';
})(%s)
"""


async def find_sitekey(tab):
    # A normal widget carries data-sitekey. A widget drawn by
    # grecaptcha.render() only leaves its iframe, with k=<sitekey>.
    found = await tab.query(
        '.g-recaptcha[data-sitekey], '
        'iframe[src*="recaptcha/api2/anchor"]',
        timeout=10,
    )
    if found.tag_name == 'iframe':
        src = found.get_attribute('src')
        return parse_qs(urlparse(src).query)['k'][0]
    return found.get_attribute('data-sitekey')


async def solve(sitekey, url):
    result = await solver.recaptcha(sitekey, url)
    return result['code']


async def fill_token(tab, token):
    reply = await tab.execute_script(
        FILL_JS % json.dumps(token), return_by_value=True)
    outcome = reply['result']
    if 'exceptionDetails' in outcome:
        error = outcome['exceptionDetails']['exception']
        raise RuntimeError(error['description'])
    return outcome['result']['value']  # True if a callback ran


async def main():
    options = ChromiumOptions()
    options.headless = True  # set to False to watch the window
    async with Chrome(options=options) as browser:
        tab = await browser.start()
        await tab.go_to(PAGE)
        sitekey = await find_sitekey(tab)
        token = await solve(sitekey, await tab.current_url())
        if not await fill_token(tab, token):
            button = await tab.query('form button[type="submit"]')
            async with tab.expect_navigation():
                await button.click()
        print(await tab.title())


asyncio.run(main())

async def solve_page(tab):
    sitekey = await find_sitekey(tab)
    token = await solve(sitekey, await tab.current_url())
    await fill_token(tab, token)
    button = await tab.query('form button[type="submit"]')
    async with tab.expect_navigation():
        await button.click()
    return await tab.title()


async def main():
    options = ChromiumOptions()
    options.headless = True
    async with Chrome(options=options) as browser:
        await browser.start()
        # One browser context per tab: tabs in the default context
        # share cookies, and a second page load can replace the first
        # tab's session or CSRF cookie.
        contexts = [await browser.create_browser_context() for _ in range(2)]
        tabs = [
            await browser.new_tab(PAGE, browser_context_id=context)
            for context in contexts
        ]
        print(await asyncio.gather(*[solve_page(tab) for tab in tabs]))
        for context in contexts:
            await browser.delete_browser_context(context)


asyncio.run(main())

# CapSkip on another Windows PC, in Server mode
solver = AsyncCapSkip(
    host='192.168.1.50',  # that PC's network address
    port=8080,
    apiKey='YOUR_API_KEY',  # only if API key validation is on
)