scrapy模拟登陆强智教务系统

引言

前面已经分享过用requests库来模拟登陆强智，这次打算用scrapy框架试一下，结果遇到的坑还真不少。

思路分析

前面已经分享过了，这里就不重复造轮子了，请出门，然后右转。传送门
这篇文章的主要目的是记录用scrapy框架模拟登陆强智教务系统遇到的问题和解决方法。

问题分析

首先，遇到的最大问题就是302重定向，scrapy框架默认是不能处理302重定向的，需要在发送请求时，加入dont_redirect

meta={'dont_redirect': True, 'handle_httpstatus_list': [302]}

然后，需要在响应头中拿到Location的URL，这里要注意，拿到的URL是bytes类型，需要转换成str类型才能使用（decode一下就好了）。

location_url = bytes.decode(response.headers.getlist('Location')[0])

最后，验证码识别的问题，这里采用的是手工识别，如果想要实现自动化，可以去网上找验证码的识别平台，直接调用API接口即可。

项目目录

代码

settings.py

# -*- coding: utf-8 -*-

# Scrapy settings for sdust project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://docs.scrapy.org/en/latest/topics/settings.html
#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'sdust'

SPIDER_MODULES = ['sdust.spiders']
NEWSPIDER_MODULE = 'sdust.spiders'

# Crawl responsibly by identifying yourself (and your website) on the user-agent
# USER_AGENT = 'sdust (+http://www.yourdomain.com)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# Configure maximum concurrent requests performed by Scrapy (default: 16)
# CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)
# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
# DOWNLOAD_DELAY = 1
# The download delay setting will honor only one of:
# CONCURRENT_REQUESTS_PER_DOMAIN = 16
# CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)
# COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)
# TELNETCONSOLE_ENABLED = False

# Override the default request headers:
DEFAULT_REQUEST_HEADERS = {
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
    'Accept-Language': 'en',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36'
}

# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
# SPIDER_MIDDLEWARES = {
#    'sdust.middlewares.SdustSpiderMiddleware': 543,
# }

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
# DOWNLOADER_MIDDLEWARES = {
#    'sdust.middlewares.SdustDownloaderMiddleware': 543,
# }

# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
# EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
# }

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
    'sdust.pipelines.SdustPipeline': 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
# AUTOTHROTTLE_ENABLED = True
# The initial download delay
# AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
# AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
# AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
# AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
# HTTPCACHE_ENABLED = True
# HTTPCACHE_EXPIRATION_SECS = 0
# HTTPCACHE_DIR = 'httpcache'
# HTTPCACHE_IGNORE_HTTP_CODES = []
# HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

jwgl.py

# -*- coding: utf-8 -*-
import scrapy
import os
from PIL import Image
from scrapy.http import Request, FormRequest


class JwglSpider(scrapy.Spider):
    name = 'jwgl'
    allowed_domains = ['jwgl.sdust.edu.cn']
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36',
        'Referer': 'http://jwgl.sdust.edu.cn/',
        'Origin': 'http://jwgl.sdust.edu.cn'
    }

    def start_requests(self):
        start_url = 'http://jwgl.sdust.edu.cn/'
        yield Request(url=start_url, callback=self.parse_login_page, headers=self.headers)

    def parse_login_page(self, response):
        captcha_url = "http://jwgl.sdust.edu.cn" + response.xpath('//img[@id="SafeCodeImg"]/@src').get()
        if not os.path.exists('../captcha/'):
            os.makedirs('../captcha/')
        yield Request(url=captcha_url, callback=self.get_captcha, headers=self.headers)

    def get_captcha(self, response):
        with open('../captcha/captcha.png', 'wb') as f:
            f.write(response.body)
        yield FormRequest(url='http://jwgl.sdust.edu.cn/Logon.do?method=logon&flag=sess', callback=self.login,
                          headers=self.headers)

    def login(self, response):
        # 用户名
        username = ''
        # 密码
        password = ''
        # 加密算法
        dataStr = response.text
        scode = dataStr.split("#")[0]
        sxh = dataStr.split("#")[1]
        code = username + "%%%" + password
        encoded = ""
        i = 0
        while i < len(code):
            if i < 20:
                encoded += code[i:i+1] + scode[0:int(sxh[i:i+1])]
                scode = scode[int(sxh[i:i+1]):len(scode)]
            else:
                encoded += code[i: len(code)]
                i = len(code)
            i += 1
        # 手工识别验证码
        image = Image.open('../captcha/captcha.png')
        image.show()
        captcha = input("请输入验证码：")
        data = {
            'view': '0',
            'encoded': encoded,
            'RANDOMCODE': captcha
        }
        yield FormRequest(url='http://jwgl.sdust.edu.cn/Logon.do?method=logon', formdata=data, callback=self.parse_location, headers=self.headers, meta={'dont_redirect': True, 'handle_httpstatus_list': [302]})

    def parse_location(self, response):
        error = response.xpath('//font[@color="red"]/text()').get()
        if error:
            print(error)
        else:
            location_url = bytes.decode(response.headers.getlist('Location')[0])
            yield Request(url=location_url, callback=self.get_main_page, headers=self.headers, meta={'dont_redirect': True, 'handle_httpstatus_list': [302]})

    def get_main_page(self, response):
        location_url = bytes.decode(response.headers.getlist('Location')[0])
        yield Request(url=location_url, headers=self.headers, callback=self.parse)

    def parse(self, response):
        print("登陆成功！")
        info = response.xpath('//div[@class="Nsb_top_menu_nc"]/text()').get()
        print("个人信息："+info)