文献批量下载器——Python源码+

资讯 3年前
1.99K

PyCNKi下载器使用教程

PyCNKi下载器源码

(百度链接里有.ipynb格式源码)

一、导入库

from selenium import webdriverfrom selenium.webdriver import ChromeOptionsfrom selenium.webdriver.chrome.options import Optionsimport openpyxlimport reimport timefrom selenium.webdriver.common.by import Byfrom selenium.webdriver.support.ui import WebDriverWaitfrom selenium.webdriver.support.select import Selectimport urllib.error

二、打开知网并进行初始设置

#无可视化界面操作def wu_visual():    chrome_options = Options()    chrome_options.add_argument('--headless')    chrome_options.add_argument('--disable-gpu')    return chrome_options
def fan_jiance():    option = ChromeOptions()    option.add_experimental_option('excludeSwitches', ['enable-automation'])    #option.add_argument('-kiosk')    return optiondef url_error_test(url,bro):    try:        bro.get(url)        print("OK")    except urllib.error.HTTPError as e:        print(e.code)        print(e.reason)    except urllib.error.URLError as e:        print(e.reason)    return e.reason
chrome_options=wu_visual()option=fan_jiance()chrome_path =r'./chromedriver.exe'bro = webdriver.Chrome(executable_path=chrome_path,chrome_options=chrome_options,options=option)
#用火狐的朋友可以把下一行代码的“#”去掉即可#bro = webdriver.Firefox()
bro.maximize_window() #最大化url = r'http://kns.cnki.net' #知网网址bro.get(url)

三、关键词搜索

#模拟输入关键字查询#请选择您需要使用的查询方式,本代码只提供标题查询input_title = bro.find_element_by_id("txt_SearchText")input_title.click()time.sleep(2)key_value = input("请输入你要下载的论文标题:")
input_title.send_keys(key_value)#点击搜索div_search = bro.find_element_by_xpath('/html/body/div[1]/div[2]/div/div[1]/input[2]')div_search.click()time.sleep(1)#点击期刊论文default_1=20bro.find_element_by_xpath("/html/body/div[5]/div[1]/div/ul[1]/li[1]/a/span").click()time.sleep(10)total_num = bro.find_element_by_xpath("/html/body/div[5]/div[1]/div/ul[1]/li[1]/a/em")if int(total_num.text)<=default_1:    print("一共搜索到"+total_num.text+"条结果")    print("共一页")else:    print("一共搜索到" + total_num.text + "条结果")    total_page =bro.find_element_by_xpath('/[@id="gridTable"]/div[2]/span[1]')    print(total_page.text)    num =int(total_page.text[1:-1])

四、选择下载格式及批量下载到几页

print("1:PDF格式2:CAJ格式请输入下载文件的格式对应数字:")load_num = int(input("请输入1 or 2:"))
print("请输入您要下载到第几页码:")

五、开始批量下载

load_page = int(input())while load_page>num or load_page<=0:    print("输入页码错误,请重新输入:")    load_page = int(input("请输入1 or 2:"))bro_new = webdriver.Chrome(executable_path=chrome_path, chrome_options=chrome_options,options=option)if int(total_num.text)<=default_1:    url_link = bro.find_elements_by_xpath('/[@id="gridTable"]/table/tbody/tr/td[2]/a')    for link_1 in url_link:        count=1        link = url + r'/kcms/detail/detail.aspx?' + link_1.get_attribute("href")[20:]        bro_new = webdriver.Chrome(executable_path=chrome_path,chrome_options=chrome_options,options=option)        bro_new.get(link)        bro_new.maximize_window()        # print("编号为"+str(count)+"的论文:"+bro_new.find_element_by_xpath("/html/body/div[2]/div[1]/div[3]/div/div[1]/div[3]/div[1]/h1").text+"————正在下载")        time.sleep(10)        if bro_new.find_element_by_xpath('/html/body/div[2]/div').text == "URL参数错误":            print("编号为"+str(count)+"的论文:"+bro_new.find_element_by_xpath("/html/body/div[2]/div[1]/div[3]/div/div[1]/div[3]/div[1]/h1").text+"————论文下载失败")            bro_new.quit()            count += 1            continue        if load_num == 1:            bro_new.find_element_by_id('pdfDown').click()            time.sleep(10)            print("编号为" + str(count) + "的论文:" + bro_new.find_element_by_xpath("/html/body/div[2]/div[1]/div[3]/div/div[1]/div[3]/div[1]/h1").text + "————下载成功")            count += 1            bro_new.quit()        if load_num == 2:            bro_new.find_element_by_id('cajDown').click()            time.sleep(10)            print("编号为" + str(count) + "的论文:" + bro_new.find_element_by_xpath("/html/body/div[2]/div[1]/div[3]/div/div[1]/div[3]/div[1]/h1").text + "————下载成功")            count += 1            bro_new.quit()else:    for ii in range(0,load_page):        count=1        url_link = bro.find_elements_by_xpath('/[@id="gridTable"]/table/tbody/tr/td[2]/a')        for link_1 in url_link:            link = url + r'/kcms/detail/detail.aspx?' + link_1.get_attribute("href")[20:]            bro_new = webdriver.Chrome(executable_path=chrome_path,chrome_options=chrome_options,options=option)            bro_new.get(link)            bro_new.maximize_window()            time.sleep(10)            if bro_new.find_element_by_xpath('/html/body/div[2]/div').text == "URL参数错误":                bro_new.quit()                print("编号为" + str(count) + "的论文:" + bro_new.find_element_by_xpath("/html/body/div[2]/div[1]/div[3]/div/div[1]/div[3]/div[1]/h1").text + "————论文下载失败")                bro_new.quit()                count += 1                continue            if load_num == 1:                bro_new.find_element_by_name('pdfDown').click()                time.sleep(10)                print("编号为" + str(count) + "的论文:" + bro_new.find_element_by_xpath("/html/body/div[2]/div[1]/div[3]/div/div[1]/div[3]/div[1]/h1").text + "————下载成功")                count += 1                bro_new.quit()            if load_num == 2:                bro_new.find_element_by_name('cajDown').click()                time.sleep(5)                print("编号为" + str(count) + "的论文:" + bro_new.find_element_by_xpath("/html/body/div[2]/div[1]/div[3]/div/div[1]/div[3]/div[1]/h1").text + "————下载成功")                count += 1                bro_new.quit()        bro.find_element_by_xpath('/[@id="PageNext"]').click()        time.sleep(10)


© 版权声明

相关文章