python通过selenium爬取百度文库
参考
https://blog.csdn.net/c406495762/article/details/72331737
https://blog.csdn.net/c406495762/article/details/72331737
运行平台: Windows Python版本: Python3.6
python3.6的docx模块和2.7的不同,直接pip安装会提示缺少依赖
需要先进入pycharm目录 安装python_docx-0.8.7-py2.py3-none-any.whl
pip install python_docx-0.8.7-py2.py3-none-any.whl
再安装docx
pip install docx
python_docx-0.8.7-py2.py3-none-any.whl下载地址:
https://download.lfd.uci.edu/pythonlibs/r5uhg2lo/python_docx-0.8.7-py2.py3-none-any.whl
由于网页的百度文库页面复杂,可能抓取内容不全,因此使用User-Agent,模拟手机登录,然后打印文章标题,文章页数,并进行翻页。
谷歌浏览器需要设置User-Agent
# -*- coding: utf-8 -*- from selenium import webdriver from bs4 import BeautifulSoup from docx import Document from docx.enum.text import WD_ALIGN_PARAGRAPH# 用来居中显示标题 from time import sleep #目的URL DEST_URL='https://wenku.baidu.com/view/8962c8dfb9f3f90f76c61b69.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: #按钮剩余多少未读 #page = driver.find_element_by_xpath( "//div[@class='pagerwg-schedule']") #按钮加载更多 点击继续阅读还是会出现点击加载更多 直接点击加载更多一了百了 next_page = driver.find_element_by_class_name("pagerwg-button") #下拉到最下方 station = driver.find_element_by_xpath( "//div[@class='bottombarwg-root border-none']") driver.execute_script('arguments[0].scrollIntoView(false);', station) # 防止页面加载过慢 sleep(5) next_page.click() except: #结束条件 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 # 得到正文内容 doc_content_list.append(text) # 防止页面加载过慢 sleep(5) 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] #在当前脚本路径存储docx文件 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 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Mobile Safari/537.36"') 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()