Python实现的爬取百度文库功能示例

时间:2021-05-22

本文实例讲述了Python实现的爬取百度文库功能。分享给大家供大家参考,具体如下:

# -*- coding: utf-8 -*-from selenium import webdriverfrom bs4 import BeautifulSoupfrom docx import Documentfrom docx.enum.text import WD_ALIGN_PARAGRAPH# 用来居中显示标题from time import sleepfrom selenium.webdriver.common.keys import Keys# 浏览器安装路径#BROWSER_PATH=\'C:\Users\Administrator\AppData\Local\Google\Chrome\Application\chromedriver.exe'#目的URLDEST_URL='https://wenku.baidu.com/view/aa31a84bcf84b9d528ea7a2c.html'#用来保存文档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): # 得到标题 title_result = soup1.find('div', attrs={'class': 'doc-title'}) doc_title = title_result.get_text() # 得到文档标题 # 拖动滚动条 init_page = driver.find_element_by_xpath( "//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( "//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( "//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: #结束条件 print("找不到元素") stop_condition = True #next_page.send_keys(Keys.ENTER) # 遍历所有的txt标签标定的文档,将其空格删除,然后进行保存 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) # 得到正文内容 sleep(2) # 防止页面加载过慢 if stop_condition is False: doc_title, doc_content_list = find_doc(driver, init) return doc_title, doc_content_listdef save(doc_title, doc_content_list): document = Document() heading = document.add_heading(doc_title, 0) heading.alignment = WD_ALIGN_PARAGRAPH.CENTER # 居中显示 for each in doc_content_list: document.add_paragraph(each) # 处理字符编码问题 t_title = doc_title.split()[0] #print(t_title) #document.save('2.docx') document.save('百度文库-%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()

更多关于Python相关内容可查看本站专题:《Python Socket编程技巧总结》、《Python正则表达式用法总结》、《Python数据结构与算法教程》、《Python函数使用技巧总结》、《Python字符串操作技巧汇总》、《Python入门与进阶经典教程》及《Python文件与目录操作技巧汇总》

希望本文所述对大家Python程序设计有所帮助。

声明:本页内容来源网络,仅供用户参考;我单位不保证亦不表示资料全面及准确无误,也不保证亦不表示这些资料为最新信息,如因任何原因,本网内容或者用户因倚赖本网内容造成任何损失或损害,我单位将不会负任何法律责任。如涉及版权问题,请提交至online#300.cn邮箱联系删除。

相关文章