您好,登錄后才能下訂單哦!
本文實例講述了Python實現的爬取百度文庫功能。分享給大家供大家參考,具體如下:
# -*- coding: utf-8 -*- from selenium import webdriver from bs4 import BeautifulSoup from docx import Document from docx.enum.text import WD_ALIGN_PARAGRAPH# 用來居中顯示標題 from time import sleep from selenium.webdriver.common.keys import Keys # 瀏覽器安裝路徑 #BROWSER_PATH=\'C:\Users\Administrator\AppData\Local\Google\Chrome\Application\chromedriver.exe' #目的URL DEST_URL='https://wenku.baidu.com/view/aa31a84bcf84b9d528ea7a2c.html' #用來保存文檔 doc_title = '' doc_content_list = [] def find_doc(driver, init=True): global doc_content_list global doc_title stop_condition = False html = driver.page_source soup1 = BeautifulSoup(html, 'lxml') if (init is True): # 得到標題 title_result = soup1.find('div', attrs={'class': 'doc-title'}) doc_title = title_result.get_text() # 得到文檔標題 # 拖動滾動條 init_page = driver.find_element_by_xpath( "http://div[@class='foldpagewg-text-con']") print(type(init_page), init_page) driver.execute_script('arguments[0].scrollIntoView();', init_page) init_page.click() init = False else: try: page = driver.find_element_by_xpath( "http://div[@class='pagerwg-schedule']") #print(type(next_page), next_page) next_page = driver.find_element_by_class_name("pagerwg-button") station = driver.find_element_by_xpath( "http://div[@class='bottombarwg-root border-none']") driver.execute_script('arguments[0].scrollIntoView(false);', station) #js.executeScript("arguments[0].click();",next_page); #sleep(5) '''js = "window.scrollTo(508,600)" driver.execute_script(js)''' next_page.click() except: #結束條件 print("找不到元素") stop_condition = True #next_page.send_keys(Keys.ENTER) # 遍歷所有的txt標簽標定的文檔,將其空格刪除,然后進行保存 content_result = soup1.find_all('p', attrs={'class': 'txt'}) for each in content_result: each_text = each.get_text() if ' ' in each_text: text = each_text.replace(' ', '') else: text = each_text # print(each_text) doc_content_list.append(text) # 得到正文內容 sleep(2) # 防止頁面加載過慢 if stop_condition is False: doc_title, doc_content_list = find_doc(driver, init) return doc_title, doc_content_list def save(doc_title, doc_content_list): document = Document() heading = document.add_heading(doc_title, 0) heading.alignment = WD_ALIGN_PARAGRAPH.CENTER # 居中顯示 for each in doc_content_list: document.add_paragraph(each) # 處理字符編碼問題 t_title = doc_title.split()[0] #print(t_title) #document.save('2.docx') document.save('百度文庫-%s.docx'% t_title) print("\n\nCompleted: %s.docx, to read." % t_title) driver.quit() if __name__ == '__main__': options = webdriver.ChromeOptions() options.add_argument('user-agent="Mozilla/5.0 (Linux; Android 4.0.4; \ Galaxy Nexus Build/IMM76B) AppleWebKit/535.19 (KHTML, like Gecko) \ Chrome/18.0.1025.133 Mobile Safari/535.19"') #driver = webdriver.Chrome(BROWSER_PATH, chrome_options=options) driver = webdriver.Chrome(chrome_options=options) driver.get(DEST_URL) #JavascriptExecutor js = (JavascriptExecutor) driver; print("**********START**********") title, content = find_doc(driver, True) save(title, content) driver.quit()
更多關于Python相關內容可查看本站專題:《Python Socket編程技巧總結》、《Python正則表達式用法總結》、《Python數據結構與算法教程》、《Python函數使用技巧總結》、《Python字符串操作技巧匯總》、《Python入門與進階經典教程》及《Python文件與目錄操作技巧匯總》
希望本文所述對大家Python程序設計有所幫助。
免責聲明:本站發布的內容(圖片、視頻和文字)以原創、轉載和分享為主,文章觀點不代表本網站立場,如果涉及侵權請聯系站長郵箱:is@yisu.com進行舉報,并提供相關證據,一經查實,將立刻刪除涉嫌侵權內容。