python 基础中requests 验证码

古诗文 验证码登录

方法1：采用bs4可以

import requests

# 古诗文网登录页面的URL地址
url = 'https://so.gushiwen.cn/user/login.aspx?from=http://so.gushiwen.cn/user/collect.aspx'

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36'
}

# 获取网络源代码
response = requests.get(url=url, headers=headers)
content = response.text

# 使用BeautifulSoup来解析网页源码，获取__VIEWSTATE和__VIEWSTATEGENERATOR参数
from bs4 import BeautifulSoup

soup = BeautifulSoup(content, 'lxml')

# 获取__VIEWSTATE
VIEWSTATE = soup.select('#__VIEWSTATE')[0].attrs.get('value')
print('VIEWSTATE: ', VIEWSTATE)

# 获取__VIEWSTATEGENERATOR
VIEWSTATEGENERATOR = soup.select('#__VIEWSTATEGENERATOR')[0].attrs.get('value')
print('VIEWSTATEGENERATOR: ', VIEWSTATEGENERATOR)

# 获取验证码图片
code = soup.select('#imgCode')[0].attrs.get('src')
code_url = 'https://so.gushiwen.cn' + code

# import urllib.request
# urllib.request.urlretrieve(url=code_url,filename='code.jpg')
session = requests.session()
# 验证码url的内容
response_code = session.get(code_url)

# webbrowser.open(code_url)

# 图片下载要使用二进制数据
content_code = response_code.content
# wb模式就是将二进制数据写入文件
with open('code.jpg', 'wb') as fp:
    fp.write(content_code)

# 获取验证码图片后，下载到本地，观察本地验证码，在控制台输入code
code_name = input('请输入登录验证码：')

# 点击登录
url_post = 'https://so.gushiwen.cn/user/login.aspx?from=http%3a%2f%2fso.gushiwen.cn%2fuser%2fcollect.aspx'

data_post = {
    '__VIEWSTATE': VIEWSTATE,
    '__VIEWSTATEGENERATOR': VIEWSTATEGENERATOR,
    'from': 'http://so.gushiwen.cn/user/collect.aspx',
    'email': '350116901@qq.com',
    'pwd': 'dhc123456',
    'code': code_name,
    'denglu': '登录'
}

# 获取网络源代码（这里能用requests对象，要用验证码的session对象，保持一个Cookie环境）
response_post = session.post(url=url_post, headers=headers, data=data_post)
content_post = response_post.text
with open('denglu.html','w',encoding='utf-8') as pf:
    pf.write(content_post)

方法2 采用xpath 不行 不知道为什么

import requests
from lxml import etree
# 古诗文网登录页面的URL地址
url = 'https://so.gushiwen.cn/user/login.aspx?from=http://so.gushiwen.cn/user/collect.aspx'

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36'
}

# 获取网络源代码
response = requests.get(url=url, headers=headers)
content = response.text

context_html = etree.HTML(content)

VIEWSTATE = context_html.xpath("//input[@id='__VIEWSTATE']/@value")[0]
VIEWSTATEGENERATOR = context_html.xpath("//input[@id='__VIEWSTATEGENERATOR']/@value")[0]
img_code = context_html.xpath("//img[@id='imgCode']/@src")[0]
print(VIEWSTATE)
print(VIEWSTATEGENERATOR)
print(img_code)

urlcode = 'https://www.gushiwen.cn' + img_code

session11 = requests.session()
response_code = session11.get(urlcode)
context_code = response_code.content
with open('image1.jpg', 'wb') as f:
    f.write(context_code)
# webbrowser.open(urlcode)
input_code = input('请输入验证码 ')
data_post = {
'__VIEWSTATE':VIEWSTATE,
'__VIEWSTATEGENERATOR':VIEWSTATEGENERATOR,
'from': 'https://so.gushiwen.cn/user/login.aspx',
'email': '350116901@qq.com',
'pwd': 'dhc123456',
'code':input_code,
'denglu': '登录'
}

r = session11.post(url=url, headers=headers,data=data_post)
r_post = r.text
# print(r_post)
with open('gushiwen.html','w',encoding='utf-8') as pf:
    pf.write(r_post)