def crack_sougou(self, url):
log.info('------开始处理未成功的URL：{}'.format(url))
if re.search('weixin\.sogou\.com', url):
log.info('------开始处理搜狗验证码------')
self.driver.get(url)
time.sleep(2)
if '搜公众号' in self.driver.page_source:
log.info('浏览器页面正常' + '直接返回')
log.info('title {}'.format(self.driver.title))
return '正确'
try:
img = self.wait.until(
EC.presence_of_element_located((By.ID, 'seccodeImage')))
log.info('------出现验证码页面------')
location = img.location
size = img.size
left = location['x']
top = location['y']
right = location['x'] + size['width']
bottom = location['y'] + size['height']
screenshot = self.driver.get_screenshot_as_png()
screenshot = Image.open(BytesIO(screenshot))
captcha = screenshot.crop((left, top, right, bottom))
captcha_path = get_captcha_path()
captcha.save(captcha_path)
captcha_name = os.path.basename(captcha_path)
try:
# raise RuntimeError
captch_input = ''
files = {
'img': (captcha_name, open(captcha_path,
'rb'), 'image/png', {})
}
res = requests.post(url=GETCAPTCHA_URL,
files=files,
timeout=self.timeout)
res = res.json()
if res.get('Success'):
captch_input = res.get('Captcha')
except Exception as e:
log.info('本地识别搜狗验证码获取异常，使用打码平台：{}'.format(e))
with open(captcha_path, "rb") as f:
filebytes = f.read()
captch_input = captch_upload_image(filebytes)
# log.info('------验证码：{}------'.format(captch_input))
log.info('------验证码：{}------'.format(captch_input))
if captch_input:
input_text = self.wait.until(
EC.presence_of_element_located(
(By.ID, 'seccodeInput')))
input_text.clear()
input_text.send_keys(captch_input)
time.sleep(1)
# from selenium.webdriver.common.keys import Keys
# self.driver.find_element_by_id("submit").send_keys(Keys.ENTER)
# log.info(driver.find_element_by_id("submit"))
#
# log.info('已经点击元素')
submit = self.wait.until(
EC.element_to_be_clickable((By.ID, 'submit')))
# time.sleep(1)
# self.driver.save_screenshot("click_after.png")
submit.click()
time.sleep(1)
# self.driver.save_screenshot("click_before.png")
# try:
if '搜公众号' not in self.driver.page_source:
# log.info('当前页面{}'.format(self.driver.page_source))
log.info('搜公众号 不在页面中验证失败')
log.info('title{}'.format(self.driver.title))
return
log.info('------验证码正确------')
return '正确'
# except Exception as e:
# log.info('--22222222----验证码输入错误------ {}'.format(e))
except Exception as e:
log.info('------未跳转到验证码页面，跳转到首页，忽略------ {}'.format(e))
elif re.search('mp\.weixin\.qq\.com', url):
log.info('------开始处理微信验证码------')
cert = random.random()
image_url = 'https://mp.weixin.qq.com/mp/verifycode?cert={}'.format(
cert)
respones = self.s.get(image_url, cookies=self.cookies)
captch_input = captch_upload_image(respones.content)
log.info('------验证码：{}------'.format(captch_input))
data = {'cert': cert, 'input': captch_input}
if self.proxies:
r = self.s.post(image_url,
cookies=self.cookies,
data=data,
proxies=self.proxies)
ret = r.json().get('ret')
log.info(ret)
if ret == 0:
log.info('------验证码正确----ret--{}'.format(ret))
log.info('------cookies已更新------{}'.format(r.status_code))
time.sleep(0.5)
else:
r = self.s.post(image_url, cookies=self.cookies, data=data)
ret = r.json().get('ret')
log.info(ret)
if ret == 0:
log.info('------验证码正确----ret--{}'.format(ret))
log.info('------cookies已更新------{}'.format(r.status_code))
def crack_sougou(self, url):
log('------开始处理未成功的URL：{}'.format(url))
if re.search('weixin\.sogou\.com', url):
log('------开始处理搜狗验证码------')
self.browser.get(url)
time.sleep(2)
if '搜公众号' in self.browser.page_source:
for i in range(30):
self.browser.get(url)
log('浏览器页面正常')
if '搜公众号' not in self.browser.page_source:
break
try:
img = self.wait.until(
EC.presence_of_element_located((By.ID, 'seccodeImage')))
log('------出现验证码页面------')
location = img.location
size = img.size
left = location['x']
top = location['y']
right = location['x'] + size['width']
bottom = location['y'] + size['height']
screenshot = self.browser.get_screenshot_as_png()
screenshot = Image.open(BytesIO(screenshot))
captcha = screenshot.crop((left, top, right, bottom))
captcha_path = os.path.join(IMAGE_DIR, CAPTCHA_NAME)
captcha.save(captcha_path)
captch_input = ''
# log('start')
files = {
'img': (CAPTCHA_NAME, open(captcha_path,
'rb'), 'image/png', {})
}
res = requests.post(url=GetCaptcha_url, files=files)
# log('end')
res = res.json()
if res.get('Success'):
captch_input = res.get('Captcha')
log('------验证码：{}------'.format(captch_input))
if captch_input:
input_text = self.wait.until(
EC.presence_of_element_located(
(By.ID, 'seccodeInput')))
input_text.clear()
input_text.send_keys(captch_input)
submit = self.wait.until(
EC.element_to_be_clickable((By.ID, 'submit')))
submit.click()
time.sleep(2)
try:
if '搜公众号' not in self.browser.page_source:
log('验证失败')
return
log('------验证码正确------')
except Exception as e:
log('--22222222----验证码输入错误------', e)
except Exception as e:
log('------未跳转到验证码页面，跳转到首页，忽略------', e)
raise RuntimeError
elif re.search('mp\.weixin\.qq\.com', url):
log('------开始处理微信验证码------')
cert = random.random()
image_url = 'https://mp.weixin.qq.com/mp/verifycode?cert={}'.format(
cert)
respones = self.s.get(image_url, cookies=self.cookies)
captch_input = captch_upload_image(respones.content)
log('------验证码：{}------'.format(captch_input))
data = {'cert': cert, 'input': captch_input}
self.s.post(image_url, cookies=self.cookies, data=data)
log('------cookies已更新------')