如何在 Windows Task Scheduler 作业中识别验证码

# PowerShell: make a job folder with its own Python environment
mkdir C:\CapSkipJobs
cd C:\CapSkipJobs
python -m venv venv
.\venv\Scripts\python.exe -m pip install capskip==1.3.0 requests

import functools
import logging
import os
import re
import sys
import time
import types

import requests
import capskip.api
from capskip import ApiException, CapSkip, NetworkException, TimeoutException

HOST = os.getenv('CAPSKIP_HOST', '127.0.0.1')
PORT = int(os.getenv('CAPSKIP_PORT', '8080'))
API_KEY = os.getenv('CAPSKIP_API_KEY', 'YOUR_API_KEY')
SITE = os.getenv('SITE_URL', 'https://example.com').rstrip('/')
USER = os.getenv('SITE_USER', 'YOUR_USERNAME')
PASSWORD = os.getenv('SITE_PASSWORD', 'YOUR_PASSWORD')
LOG_FILE = os.getenv('JOB_LOG', r'C:\CapSkipJobs\job.log')
ATTEMPTS = int(os.getenv('JOB_ATTEMPTS', '3'))
PAUSE = int(os.getenv('JOB_PAUSE', '30'))

# Task Scheduler has no environment field. User variables work:
# the next run of the task sees them, with no sign-out needed.
setx SITE_URL "https://example.com"
setx SITE_USER "YOUR_USERNAME"
setx SITE_PASSWORD "YOUR_PASSWORD"

os.makedirs(os.path.dirname(LOG_FILE), exist_ok=True)
logging.basicConfig(filename=LOG_FILE, level=logging.INFO,
                    format='%(asctime)s pid=%(process)d %(levelname)s %(message)s')
log = logging.getLogger('job')

# The SDK sets no HTTP timeouts, so give every CapSkip call one: connect 5 s, read 30 s.
# This reaches into the SDK, so the guard fails loudly if a newer version changes it.
if not hasattr(capskip.api, 'requests'):
    log.error('capskip.api.requests is gone: check the timeout patch')
    sys.exit(1)
capskip.api.requests = types.SimpleNamespace(
    RequestException=requests.RequestException,
    post=functools.partial(requests.post, timeout=(5, 30)),
    get=functools.partial(requests.get, timeout=(5, 30)))

def fetch_login(session):
    """Load the login page: the session cookie, the CSRF token and the sitekey."""
    page = session.get(SITE + '/login', timeout=(5, 30))
    if page.status_code != 200:
        raise RuntimeError('login page returned HTTP %d' % page.status_code)
    csrf = re.search(r'name="csrfmiddlewaretoken" value="([^"]+)"', page.text)
    key = re.search(r'data-sitekey="([^"]+)"', page.text)
    if not csrf or not key:
        raise RuntimeError('login page has no CSRF token or no sitekey')
    return csrf.group(1), key.group(1)


def solve(sitekey):
    solver = CapSkip(apiKey=API_KEY, host=HOST, port=PORT)
    return solver.recaptcha(sitekey=sitekey, url=SITE + '/login')['code']

def submit(session, csrf, token):
    """Post the login form, the way the browser would, Referer included."""
    resp = session.post(SITE + '/login', timeout=(5, 30),
                        headers={'Referer': SITE + '/login'},
                        data={'csrfmiddlewaretoken': csrf, 'username': USER,
                              'password': PASSWORD, 'g-recaptcha-response': token})
    # Many sites answer a failed login with 200 and the form again.
    if resp.status_code != 200 or 'type="password"' in resp.text:
        raise RuntimeError('login rejected: HTTP %d %s' % (resp.status_code, resp.text[:120]))
    log.info('login accepted: %s', resp.text[:40])

def run():
    session = requests.Session()  # a fresh session means a fresh CSRF token
    csrf, sitekey = fetch_login(session)
    log.info('solving reCAPTCHA v2, sitekey %s', sitekey)
    submit(session, csrf, solve(sitekey))


def is_retryable(exc):
    if isinstance(exc, (NetworkException, TimeoutException, requests.RequestException)):
        return True
    return isinstance(exc, ApiException) and 'UNSOLVABLE' in str(exc)

def main():
    log.info('start, CapSkip at %s:%s, site %s', HOST, PORT, SITE)
    for attempt in range(1, ATTEMPTS + 1):
        try:
            run()
            log.info('done, exit 0')
            return 0
        except Exception as exc:
            retry = is_retryable(exc)
            log.warning('attempt %d/%d failed, %s: %s: %s', attempt, ATTEMPTS,
                        'retryable' if retry else 'fatal', type(exc).__name__, exc,
                        exc_info=not retry)
            if not retry:
                return 1
            if attempt < ATTEMPTS:
                time.sleep(PAUSE)
    log.error('giving up after %d attempts, exit 3', ATTEMPTS)
    return 3


if __name__ == '__main__':
    sys.exit(main())

$python = 'C:\CapSkipJobs\venv\Scripts\python.exe'
$jobDir = 'C:\CapSkipJobs'

$action = New-ScheduledTaskAction -Execute $python `
    -Argument ('"{0}\job.py"' -f $jobDir) -WorkingDirectory $jobDir
$trigger = New-ScheduledTaskTrigger -Once -At (Get-Date).AddMinutes(1) `
    -RepetitionInterval (New-TimeSpan -Hours 1)
$settings = New-ScheduledTaskSettingsSet `
    -ExecutionTimeLimit (New-TimeSpan -Minutes 30) `
    -MultipleInstances IgnoreNew `
    -StartWhenAvailable -AllowStartIfOnBatteries -DontStopIfGoingOnBatteries

Register-ScheduledTask -TaskName 'CapSkip login job' -Action $action `
    -Trigger $trigger -Settings $settings -Force

# Run the task now instead of waiting for the trigger
Start-ScheduledTask -TaskName 'CapSkip login job'
Start-Sleep -Seconds 2

# Wait until it is no longer running
while ((Get-ScheduledTask -TaskName 'CapSkip login job').State -eq 'Running') {
    Start-Sleep -Seconds 2
}

# How did it end, and what did the job write?
Get-ScheduledTaskInfo -TaskName 'CapSkip login job' |
    Select-Object LastRunTime, LastTaskResult, NextRunTime
Get-Content C:\CapSkipJobs\job.log -Tail 6

import functools
import logging
import os
import re
import sys
import time
import types

import requests
import capskip.api
from capskip import ApiException, CapSkip, NetworkException, TimeoutException

HOST = os.getenv('CAPSKIP_HOST', '127.0.0.1')
PORT = int(os.getenv('CAPSKIP_PORT', '8080'))
API_KEY = os.getenv('CAPSKIP_API_KEY', 'YOUR_API_KEY')
SITE = os.getenv('SITE_URL', 'https://example.com').rstrip('/')
USER = os.getenv('SITE_USER', 'YOUR_USERNAME')
PASSWORD = os.getenv('SITE_PASSWORD', 'YOUR_PASSWORD')
LOG_FILE = os.getenv('JOB_LOG', r'C:\CapSkipJobs\job.log')
ATTEMPTS = int(os.getenv('JOB_ATTEMPTS', '3'))
PAUSE = int(os.getenv('JOB_PAUSE', '30'))


os.makedirs(os.path.dirname(LOG_FILE), exist_ok=True)
logging.basicConfig(filename=LOG_FILE, level=logging.INFO,
                    format='%(asctime)s pid=%(process)d %(levelname)s %(message)s')
log = logging.getLogger('job')

# The SDK sets no HTTP timeouts, so give every CapSkip call one: connect 5 s, read 30 s.
# This reaches into the SDK, so the guard fails loudly if a newer version changes it.
if not hasattr(capskip.api, 'requests'):
    log.error('capskip.api.requests is gone: check the timeout patch')
    sys.exit(1)
capskip.api.requests = types.SimpleNamespace(
    RequestException=requests.RequestException,
    post=functools.partial(requests.post, timeout=(5, 30)),
    get=functools.partial(requests.get, timeout=(5, 30)))


def fetch_login(session):
    """Load the login page: the session cookie, the CSRF token and the sitekey."""
    page = session.get(SITE + '/login', timeout=(5, 30))
    if page.status_code != 200:
        raise RuntimeError('login page returned HTTP %d' % page.status_code)
    csrf = re.search(r'name="csrfmiddlewaretoken" value="([^"]+)"', page.text)
    key = re.search(r'data-sitekey="([^"]+)"', page.text)
    if not csrf or not key:
        raise RuntimeError('login page has no CSRF token or no sitekey')
    return csrf.group(1), key.group(1)


def solve(sitekey):
    solver = CapSkip(apiKey=API_KEY, host=HOST, port=PORT)
    return solver.recaptcha(sitekey=sitekey, url=SITE + '/login')['code']


def submit(session, csrf, token):
    """Post the login form, the way the browser would, Referer included."""
    resp = session.post(SITE + '/login', timeout=(5, 30),
                        headers={'Referer': SITE + '/login'},
                        data={'csrfmiddlewaretoken': csrf, 'username': USER,
                              'password': PASSWORD, 'g-recaptcha-response': token})
    # Many sites answer a failed login with 200 and the form again.
    if resp.status_code != 200 or 'type="password"' in resp.text:
        raise RuntimeError('login rejected: HTTP %d %s' % (resp.status_code, resp.text[:120]))
    log.info('login accepted: %s', resp.text[:40])


def run():
    session = requests.Session()  # a fresh session means a fresh CSRF token
    csrf, sitekey = fetch_login(session)
    log.info('solving reCAPTCHA v2, sitekey %s', sitekey)
    submit(session, csrf, solve(sitekey))


def is_retryable(exc):
    if isinstance(exc, (NetworkException, TimeoutException, requests.RequestException)):
        return True
    return isinstance(exc, ApiException) and 'UNSOLVABLE' in str(exc)


def main():
    log.info('start, CapSkip at %s:%s, site %s', HOST, PORT, SITE)
    for attempt in range(1, ATTEMPTS + 1):
        try:
            run()
            log.info('done, exit 0')
            return 0
        except Exception as exc:
            retry = is_retryable(exc)
            log.warning('attempt %d/%d failed, %s: %s: %s', attempt, ATTEMPTS,
                        'retryable' if retry else 'fatal', type(exc).__name__, exc,
                        exc_info=not retry)
            if not retry:
                return 1
            if attempt < ATTEMPTS:
                time.sleep(PAUSE)
    log.error('giving up after %d attempts, exit 3', ATTEMPTS)
    return 3


if __name__ == '__main__':
    sys.exit(main())

# Only if CapSkip runs in Server mode on another Windows PC
setx CAPSKIP_HOST "192.168.1.50"
# Only if API key validation is switched on in CapSkip
setx CAPSKIP_API_KEY "YOUR_API_KEY"