def main():
browser = webdriver.Chrome('./chromedriver')
# 打开登录页面 （可以根据自己需要选择相应的网站进行自动登录）
browser.get('http://218.197.101.24')
time.sleep(1)
# 截图
"""
save_screenshot(fileName) 就是对当前页面进行截图
"""
browser.save_screenshot('./aa.png')
# 需要对验证码图片进行裁剪
# 确定验证码图片的左上角和右下角的坐标（裁剪的区域就确定）
code_img_ele = browser.find_element_by_xpath(
'//*[@id="VerifyCode"]') # 获取验证码图片
location = code_img_ele.location # 图片左上角坐标
size = code_img_ele.size # 验证码对应的长和宽
# 左上角右下角坐标， 验证码图片就确定下来了 //*[@id="J-loginImg"]
rangle = (int(location['x']), int(location['y']),
int(location['x'] + size['width']),
int(location['y'] + size['height']))
i = Image.open('./aa.png')
code_img_name = './code.png'
# 使用crop根据指定区域进行裁剪
frame = i.crop(rangle)
frame.save(code_img_name)
username_input = browser.find_element_by_xpath('//*[@id="txtUserID"]')
pwd_input = browser.find_element_by_xpath('//*[@id="txtUserPwd"]')
code_input = browser.find_element_by_xpath('//*[@id="yzm"]')
username_input.send_keys('账号')
time.sleep(1)
pwd_input.send_keys('密码')
time.sleep(1)
code_input.send_keys(chaojiying.getCodeText('./code.png', 1902))
time.sleep(1)
login_button = browser.find_element_by_xpath(
'//*[@id="ff"]/table/tbody/tr[5]/td[2]/input[1]')
login_button.click()
time.sleep(5)
browser.quit()
def main():
url = 'https://so.gushiwen.cn/user/login.aspx?from=http://so.gushiwen.cn/user/collect.aspx'
headers = {
'User-Agent':
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.0.3 Safari/605.1.15'
}
page_text = requests.get(url=url, headers=headers).text
# 解析验证码图片img中src属性值
parser = etree.HTMLParser(encoding="utf-8")
tree = etree.HTML(page_text, parser=parser)
code_img_src = 'https://so.gushiwen.cn' + tree.xpath(
'//*[@id="imgCode"]/@src')[0]
img_data = requests.get(url=code_img_src, headers=headers).content
# 将验证码保存至本地
with open('./code.jpg', 'wb') as fp:
fp.write(img_data)
# 调用打码平台的示例代码进行验证码图片识别
code = chaojiying.getCodeText('code.jpg', 1902)
print(code)
def main():
session = requests.Session()
url = 'http://www.renren.com'
headers = {
'User-Agent':
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.0.3 Safari/605.1.15'
}
page_text = session.get(url=url, headers=headers).text
tree = etree.HTML(page_text)
code_img_src = tree.xpath('//*[@id="verifyPic_login"]/@src')[0]
code_img_data = session.get(url=code_img_src, headers=headers).content
# 保存验证码图片
with open('./code.jpg', 'wb') as fp:
fp.write(code_img_data)
# 使用超级鹰代码对验证码图片进行识别
code_str = chaojiying.getCodeText('code.jpg', 1902)
print('验证码：', code_str)
# login_url = tree.xpath('//*[@id="loginForm"]/@action')
login_url = 'http://www.renren.com/PLogin.do'
data = {
'email': 'XXX',
'password': '******',
'icode': code_str,
'origURL': 'http://www.renren.com/home',
'domain': 'renren.com',
'key_id': '1',
'captcha_type': 'web_login',
'f': '',
}
# 通用验证登录成的方式是看响应状态码
response = session.post(url=login_url, headers=headers, data=data)
print(response.status_code)
resp = session.get(url='http://www.renren.com/974823124/profile',
headers=headers).text
with open('renren.html', 'w', encoding='utf-8') as fp:
fp.write(resp)
print('爬取完毕！')
# 验证码识别
import requests
import chaojiying
url = "https://so.gushiwen.cn/RandCode.ashx?t=1599137306043"
headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.83 Safari/537.36'
}
img = requests.get(url, headers=headers).content
with open('a.jpg', 'wb') as f:
f.write(img)
result = chaojiying.getCodeText('a.jpg', 1902)
print(result)
session=requests.Session()
url="http://www.renren.com/"
headers={
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.83 Safari/537.36'
}
main_text=session.get(url,headers=headers).text
soup=BeautifulSoup(main_text,"lxml")
img_src=soup.find("img",id="verifyPic_login")["src"]
# print(img_src)
img=session.get(img_src,headers=headers).content
with open("a.jpg","wb") as f:
f.write(img)
post_url="http://www.renren.com/ajaxLogin/login?1=1&uniqueTimestamp=202085110108"
codeText=chaojiying.getCodeText("a.jpg",1902)
data={
'email': '*****@*****.**',
'icode':codeText,
'origURL': 'http://www.renren.com/home',
'domain': 'renren.com',
'key_id': '1',
'captcha_type': 'web_login',
'password': "******",
'rkey': "3d1f9abdaae1f018a49d38069fe743c8"
}
response=session.post(post_url,data=data,headers=headers)
print(response.status_code)
text=json.loads(response.text)