文獻批量下載器PyCNKi使用教程
PyCNKi下載器使用教程
PyCNKi下載器源碼
(百度鏈接里有.ipynb格式源碼)
一、導入庫
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、打開知網(wǎng)并進行初始設置
#無可視化界面操作def wu_visual(): chrome_options = Options() chrome_options.a(chǎn)dd_argument('--h(huán)eadless') chrome_options.a(chǎn)dd_argument('--disable-gpu') return chrome_options
def fan_jiance(): option = ChromeOptions() option.a(chǎn)dd_experimental_option('excludeSwitches', ['enable-automation']) #option.a(chǎn)dd_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碼的“!比サ艏纯桑ro = webdriver.Firefox()
bro.maximize_window() #最大化url = r'http://kns.cnki.net' #知網(wǎng)網(wǎng)址bro.get(url)
三、關鍵詞搜索
#模擬輸入關鍵字查詢#請選擇您需要使用的查詢方式,本代碼只提供標題查詢input_title = bro.find_element_by_id("txt_SearchText")input_title.click()time.sleep(2)key_value = input("請輸入你要下載的論文標題:")
input_title.send_keys(key_value)#點擊搜索div_search = bro.find_element_by_xpath('/html/body/div[1]/div[2]/div/div[1]/input[2]')div_search.click()time.sleep(1)#點擊期刊論文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+"條結(jié)果") print("共一頁")else: print("一共搜索到" + total_num.text + "條結(jié)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、選擇下載格式及批量下載到幾頁
print("1:PDF格式2:CAJ格式請輸入下載文件的格式對應數(shù)字:")load_num = int(input("請輸入1 or 2:"))
print("請輸入您要下載到第幾頁碼:")
五、開始批量下載
load_page = int(input())while load_page>num or load_page<=0: print("輸入頁碼錯誤,請重新輸入:") load_page = int(input("請輸入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.a(chǎn)spx?' + 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("編號為"+str(count)+"的論文:"+bro_new.find_element_by_xpath("/html/body/div[2]/div[1]/div[3]/div/div[1]/div[3]/div[1]/h1").text+"————正在下載") time.sleep(10) if bro_new.find_element_by_xpath('/html/body/div[2]/div').text == "URL參數(shù)錯誤": print("編號為"+str(count)+"的論文:"+bro_new.find_element_by_xpath("/html/body/div[2]/div[1]/div[3]/div/div[1]/div[3]/div[1]/h1").text+"————論文下載失。ⅲ bro_new.quit() count += 1 continue if load_num == 1: bro_new.find_element_by_id('pdfDown').click() time.sleep(10) print("編號為" + str(count) + "的論文:" + bro_new.find_element_by_xpath("/html/body/div[2]/div[1]/div[3]/div/div[1]/div[3]/div[1]/h1").text + "————下載成功") count += 1 bro_new.quit() if load_num == 2: bro_new.find_element_by_id('cajDown').click() time.sleep(10) print("編號為" + str(count) + "的論文:" + bro_new.find_element_by_xpath("/html/body/div[2]/div[1]/div[3]/div/div[1]/div[3]/div[1]/h1").text + "————下載成功") 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.a(chǎn)spx?' + 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參數(shù)錯誤": bro_new.quit() print("編號為" + str(count) + "的論文:" + bro_new.find_element_by_xpath("/html/body/div[2]/div[1]/div[3]/div/div[1]/div[3]/div[1]/h1").text + "————論文下載失。ⅲ bro_new.quit() count += 1 continue if load_num == 1: bro_new.find_element_by_name('pdfDown').click() time.sleep(10) print("編號為" + str(count) + "的論文:" + bro_new.find_element_by_xpath("/html/body/div[2]/div[1]/div[3]/div/div[1]/div[3]/div[1]/h1").text + "————下載成功") count += 1 bro_new.quit() if load_num == 2: bro_new.find_element_by_name('cajDown').click() time.sleep(5) print("編號為" + str(count) + "的論文:" + bro_new.find_element_by_xpath("/html/body/div[2]/div[1]/div[3]/div/div[1]/div[3]/div[1]/h1").text + "————下載成功") count += 1 bro_new.quit() bro.find_element_by_xpath('/[@id="PageNext"]').click() time.sleep(10)

請輸入評論內(nèi)容...
請輸入評論/評論長度6~500個字
最新活動更多
推薦專題
- 1 UALink規(guī)范發(fā)布:挑戰(zhàn)英偉達AI統(tǒng)治的開始
- 2 北電數(shù)智主辦酒仙橋論壇,探索AI產(chǎn)業(yè)發(fā)展新路徑
- 3 降薪、加班、裁員三重暴擊,“AI四小龍”已折戟兩家
- 4 “AI寒武紀”爆發(fā)至今,五類新物種登上歷史舞臺
- 5 國產(chǎn)智駕迎戰(zhàn)特斯拉FSD,AI含量差幾何?
- 6 光計算迎來商業(yè)化突破,但落地仍需時間
- 7 東陽光:2024年扭虧、一季度凈利大增,液冷疊加具身智能打開成長空間
- 8 地平線自動駕駛方案解讀
- 9 封殺AI“照騙”,“淘寶們”終于不忍了?
- 10 優(yōu)必選:營收大增主靠小件,虧損繼續(xù)又逢關稅,能否乘機器人東風翻身?