全国图书馆参考咨询联盟模拟登陆及爬取可爬取的图片

一、编程思路

1.模拟登陆 采用selenium PhantomJS 采用Chrome Firefox 这些，我的电脑无法截取验证码位置，读者可以自行尝试 验证码识别可采用tesserocr 我采用手动输入

2、查询，获取搜索框，用户输入关键字并查询

3、页面信息，F12查看即可 ，若采用find_element_by_xpath()查询需注意element 返回是第一个节点信息 elements返回是一个列表

4、书本具体信息、F12查看，后面操作很简单

5、文献传递页面、这个地方是最难的，右键查看文献传递这个按钮，点击其中href是无法进入的，这个只是一种绑定关系，需要仔细观察进入文献传递页面前后的network中第一个文本中的信息，里面存在很多url，

只有refer 点击可以进入，分析refer url里面的元素，在进入前的那个页面的url可找到，后面采用切片即可

6、下载书名页...............，此处我采用的是观察图片的链接直接的关系，从而获取，这个地方需要注意的是，图片需要不断的滑动滑动条才能加载图片，否则无法下载

7、保存图片 ，注意 'w' 和‘wb’使用即可

8、最后需要注意爬取频率，否则很容易被发现。

from selenium import webdriver
import time
#import tesserocr
import pytesseract
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import Select
from PIL import Image
import requests
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
# from pyquery import PyQuery as pq
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
from lxml import etree
from urllib.parse import quote
import os

# cookie_bro = browser.get_cookies()
#
# cookie1=cookie_bro[1]['value']
# print('获取cookie成功')
def login():
    #输入用户名
    input_user = browser.find_element_by_id("userName")     #查找输入框
    input_user.send_keys("ckho")
    time.sleep(2)

    #输入密码
    input_pwd = browser.find_element_by_id("passWord")
    input_pwd.send_keys("chen13560034370")
    time.sleep(2)

    #选择
    input_gid = Select(browser.find_element_by_id("gid"))   #实例化input_gid
    input_gid.select_by_value("7320")                       #选择class=7320的选择
    browser.save_screenshot("screen.png")
    # 定位验证码图片的位置，并截取该位置的图片
    code_element = browser.find_element_by_id("vimg")
    print(code_element.location) # {'x': 548, 'y': 523}
    left = code_element.location['x']
    top = code_element.location['y']
    right = code_element.size['width'] + left
    height = code_element.size['height'] + top
    im = Image.open("screen.png")
    img = im.crop((left, top, right, height))
    img.save("screen4.png")
    #验证码识别
    try:
        input_verify = wait.until(
            EC.element_to_be_clickable((By.ID,"verifyCode"))
        )#browser.find_element_by_id("verifyCode")
        result = input("请输入验证码")
        input_verify.send_keys(result)
        #单击登录
        enter = wait.until(
            EC.element_to_be_clickable((By.ID,"submit"))
        )#browser.find_element_by_id("submit").click()
        enter.click()
        print("登录成功")
        browser.save_screenshot("screen6.png")
        return browser.current_url
    except BaseException:
        print(" Enter Error")

#查询书籍信息并且用户可选择页数
def index_page(url):
    book_name = input("请输入查找的书名")
    input_bookname = browser.find_element_by_id("sw").send_keys(book_name)
    enter = browser.find_element_by_xpath('//*[@id="f2"]/div[2]/input[1]').click()
    print("当前页数为第一页")
    all_book_information()
    page = input("请输入想看页数：")
    print("...正在爬取第"+str(page)+"页")
    current_url = browser.current_url #输入书名后的页面的链接
    try:
        if int(page)>1:
            browser.get(current_url)
            print(current_url)
            #查找输入框
            input_page = wait.until(
                EC.presence_of_element_located((By.CSS_SELECTOR, "#jpage"))
            )
            #查找登录建
            sumbit = wait.until(
                EC.element_to_be_clickable((By.CSS_SELECTOR, '#pageinfo > input[type=button]:nth-child(13)'))
            )
            input_page.clear()
            input_page.send_keys(str(page))
            sumbit.click()
        all_book_information()
        return browser.current_url #换页后的链接
    except TimeoutError:
        index_page()

def all_book_information():
    #返回当前页面的书本信息
    addres ='//table[@class="book1"]'
    addres_list = browser.find_elements_by_xpath(addres)
    book_list = []
    for book in addres_list:
        book_list.append(book.text)
    for i in enumerate(book_list, start=1):
        print(i)


#获取每本书具体链接并且返回每本书具体信息
def get_detail_book(url):
    number = input("请输入你想要了解书的编号：")
    browser.get(url)
    addres = '//table[{}][@class="book1"]//a[@class="px14"]'.format(number)
    book_url = browser.find_element_by_xpath(addres).get_attribute("href")
    browser.get(book_url)
    detail_book_information = browser.find_elements_by_xpath('//div[@class="tubox"]//dd')
    for book in detail_book_information:
        print(book.text)

    return browser.current_url

#进入图书馆文献传递页面
def sent_book_emial(url):
    bqy_url = browser.find_element_by_xpath('//*[@id="libinfo"]/div[1]/div/a[1]').get_attribute("href")
    all_page_name(bqy_url)
    answer = input("是否需要下载此书 是请输入是1 否2 看其他书按3 ,下载书名页4 下载前言页5 下载版权页6 下载目录页7 下载正文页8")
    if int(answer)==1:
        base_url = 'http://book.ucdrs.superlib.net/gofirstdrs.jsp?'
        browser.get(url)
        sent_href = browser.find_element_by_xpath('//*[@id="libinfo"]/div[2]//a').get_attribute("href") #页面上文献传递对应href值
        #拆分href，拼接可进入图书参考咨询页面的url 通过进入文献传递，观察network中找到可进入图书参考咨询页面url，直接点击href是不能访问
        list1 = sent_href.split("?", 1)
        list2 = list1[1].split("'", 1)
        tscx_url = base_url+list2[0]
        browser.get(tscx_url)
        browser.save_screenshot("screen5.png")
        book_download()
    elif int(answer)==2:
        print("\n")
        print("本次查询结束，欢迎下次使用!")

    elif int(answer) == 4:
        browser.get(url)
        bqy_url = browser.find_element_by_xpath('//*[@id="libinfo"]/div[1]/div/a[1]').get_attribute("href")
        base_url = bqy_download(bqy_url)
        smy_img(base_url)
    elif int(answer)==5:
        browser.get(url)
        bqy_url = browser.find_element_by_xpath('//*[@id="libinfo"]/div[1]/div/a[1]').get_attribute("href")
        base_url = bqy_download(bqy_url)
        qyy_img(base_url)
    elif int(answer)==6:
        browser.get(url)
        bqy_url = browser.find_element_by_xpath('//*[@id="libinfo"]/div[1]/div/a[1]').get_attribute("href")
        base_url = bqy_download(bqy_url)
        bqy_url(base_url)
    elif int(answer)==7:
        browser.get(url)
        bqy_url = browser.find_element_by_xpath('//*[@id="libinfo"]/div[1]/div/a[1]').get_attribute("href")
        base_url = bqy_download(bqy_url)
        mly_img(base_url)
    elif int(answer)==8:
        browser.get(url)
        bqy_url = browser.find_element_by_xpath('//*[@id="libinfo"]/div[1]/div/a[1]').get_attribute("href")
        base_url = bqy_download(bqy_url)
        zwy_img(base_url)

    else:
        url = "http://www.ucdrs.superlib.net/"
        browser.get(url)
        all_book_url_page = index_page(url)
        detail_book_url = get_detail_book(all_book_url_page)
        sent_book_emial(detail_book_url)


def all_page_name(url):
    browser.get(url)
    all_page_name = browser.find_element_by_id("pagejump")
    t1 = all_page_name.text.replace(" ", "") #删除空格
    print("该书可看部分仅有:"+t1+"请按照此选择下载，否则可能导致下载错误")


#图书下载
def book_download():
    all_page = browser.find_element_by_xpath('//*[@id="content"]/form/ul/li[3]/p[1]').text
    print(all_page)
    print("每本图书咨询每次不超过50页")
    input1 = input("请输入想看的书初始页")
    input2 = input("请输入想看的书的末页")
    input_start = browser.find_element_by_id("frompage").send_keys(input1)
    input_led = browser.find_element_by_id("endpage").send_keys(input2)
    email = input("请输入你的邮箱账号")
    input_email = browser.find_element_by_id("email").send_keys(email)
    verifycode1 = input("请输入验证码")
    input_verifycode1 = browser.find_element_by_id("verifycode").send_keys(verifycode1)
    input_enter = browser.find_element_by_xpath('//li[@class="sumbit"]').click()

#返回图片的url共同部分
def bqy_download(url):
    browser.get(url)
    print(url)
    time.sleep(4) #注意 需要留个页面加载时间，模仿人阅读时候网页加载速度  否则加载不出来想要的图片链接
    browser.save_screenshot("screen8.png")
    first_img_url = browser.find_element_by_xpath('//*[@id="reader"]/div/div[1]/input').get_attribute("src")
    print(first_img_url)
    base_url = first_img_url[0:-13]
    print(base_url)
    return base_url

#下载书名页
def smy_img(base_url):
    i=1
    print("仅下载1页")
    while i<2:
            img_url = base_url + 'bok00{}'.format(i) + '?zoom=0&f=0'
            i += 1
            response = requests.get(img_url)
            print(img_url)
            with open("D:/pycharm/实战案例/前言页/" + str(i-1) + '.png', "wb") as f:
                f.write(response.content)
                print("success download")


            time.sleep(2)

#下载版权页
def bqy_img(base_url):
    i=1
    print("仅下载1页")
    while i<2:
            img_url = base_url + 'leg00{}'.format(i) + '?zoom=0&f=0'
            i += 1
            response = requests.get(img_url)
            print(img_url)
            with open("D:/pycharm/实战案例/版权页/" + str(i-1) + '.png', "wb") as f:
                f.write(response.content)
                print("success download")


#下载前言页
def qyy_img(base_url):
    i=1
    print("仅下载5页")
    while i<6:
            img_url = base_url + 'fow00{}'.format(i) + '?zoom=0&f=0'
            i += 1
            response = requests.get(img_url)
            print(img_url)
            with open("D:/pycharm/实战案例/前言页/" + str(i-1) + '.png', "wb") as f:
                f.write(response.content)
                print("success download")
            # try:
            #     response.headers["Accept-Encoding"]
            # except:
            #     break
            time.sleep(2)

#下载目录页
def mly_img(base_url):
    i=1
    print("仅下载3页")
    while i<4:
            img_url = base_url + '!0000{}'.format(i) + '?zoom=0&f=0'
            i += 1
            response = requests.get(img_url)
            print(img_url)
            with open("D:/pycharm/实战案例/目录页/" + str(i-1) + '.png', "wb") as f:
                f.write(response.content)
                print("success download")
            time.sleep(2)

#下载正文页
def zwy_img(base_url):
    i=1
    print("仅下载15页")
    while i<12:
            if i<16:
                img_url = base_url + '00000{}'.format(i) + '?zoom=0&f=0'
            else:
                img_url = base_url + '0000{}'.format(i) + '?zoom=0&f=0'
            i += 1
            response = requests.get(img_url)
            print(img_url)
            with open("D:/pycharm/实战案例/正文页/" + str(i-1) + '.png', "wb") as f:
                f.write(response.content)
                print("success download")
            time.sleep(2)


if __name__ == '__main__':
    url = "http://www.ucdrs.superlib.net/login/login.action"
    # headers = {
    #      "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
    #     "Accept-Encoding": "gzip, deflate",
    #     "Accept-Language": "zh-CN,zh;q=0.9",
    #     "Cache-Control": "max-age=0",
    #     "Connection": "keep-alive",
    #     "Cookie": "JSESSIONID=E9B8FFC8B023F0FC12A07A3ECDE91581.jp26; __dxca=d04d4dbb-57fb-4114-b080-190507ee4cbf; route=5ead36b501ee59635125fd6ef4221d0e; UM_distinctid=170b290e53493e-0372017c841b37-4313f6a-144000-170b290e5364a3; CNZZDATA2088844=cnzz_eid%3D382770322-1583543803-%26ntime%3D1583551301",
    #     "Host": "img.duxiu.com",
    #     "Upgrade-Insecure-Requests":"1",
    #     "User-Agent":'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36'
    # }
    #
    # cookies = {
    #     "Cookie": "JSESSIONID=E9B8FFC8B023F0FC12A07A3ECDE91581.jp26; __dxca=d04d4dbb-57fb-4114-b080-190507ee4cbf; route=5ead36b501ee59635125fd6ef4221d0e; UM_distinctid=170b290e53493e-0372017c841b37-4313f6a-144000-170b290e5364a3; CNZZDATA2088844=cnzz_eid%3D382770322-1583543803-%26ntime%3D1583551301",
    # }
    browser = webdriver.PhantomJS()
    browser.get(url)
    wait = WebDriverWait(browser, 8)
    print("欢迎使用图书查询小程序")
    login()  # 登录 需要手动验证码
    all_book_url_page = index_page(url)  # 查看第几页及返回当前页的书本信息
    detail_book_url = get_detail_book(all_book_url_page) #返回每本书的具体的链接
    sent_book_emial(detail_book_url)

若有错误，请留言告诉我，谢谢！

来源：https://www.cnblogs.com/chka/p/12447088.html