Python爬虫实战 下载原力创付费文档---滑动式（优化篇）

下载原力创付费文档—滑动式（优化篇）

大幅提升爬取速度，优化接口，提升安全可靠性，资源消耗大幅降低

一、项目需求：

从目标网址下载付费文档，并保存为word形式
网址点这里

二、思路

• 1.利用selenium实现异步加载，获取图片url
• 2.爬取图片
• 3.将图片写进word文档
• 4.将word文档转化成PDF

三、技术点

• 1.python + selenium自动化
• 2.python + docx
• 3.python + pywin32

四、环境

python3.6 + selenium + docx + pywin32

安装(推荐使用清华源)：
   pip install selenium -i https://pypi.tuna.tsinghua.edu.cn/simple/
   pip install python-docx -i https://pypi.tuna.tsinghua.edu.cn/simple/
   pip install pywin32 -i https://pypi.tuna.tsinghua.edu.cn/simple/

五、代码

import time

from selenium import webdriver
from selenium.webdriver.common import keys
import requests
from docx import Document
from docx.shared import Inches
from win32com.client import constants, gencache

class YuanLC:
 def __init__(self, url):

     self.filename = None
     
     # 创建session网络请求对象
     headers = {
     
         "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,a"
                   "pplication/signed-exchange;v=b3;q=0.9",
         "Accept-Encoding": "gzip, deflate, br",
         "Accept-Language": "zh-CN,zh;q=0.9",
         "Cache-Control": "no-cache",
         "Connection": "keep-alive",
         "Cookie": "CLIENT_SYS_UN_ID=3rvgCl9XYO1u41DVBzG/Ag==; s_v=cdh%3D%3E27a30245%7C%7C%7Cvid%3D%3E1599561"
                   "968279953439%7C%7C%7Cfsts%3D%3E1599561968%7C%7C%7Cdsfs%3D%3E0%7C%7C%7Cnps%3D%3E1; s_s=cdh%3"
                   "D%3E27a30245%7C%7C%7Clast_req%3D%3E1599561968%7C%7C%7Csid%3D%3E1599561968685697441%7C%7C%7Cd"
                   "sps%3D%3E0; __cfduid=dcce463c0931f0014f9ed1b030e9c47981599561968",
         "Host": "view-cache.book118.com",
         "Pragma": "no-cache",
         "Sec-Fetch-Dest": "document",
         "Sec-Fetch-Mode": "navigate",
         "Sec-Fetch-Site": "none",
         "Sec-Fetch-User": "?1",
         "Upgrade-Insecure-Requests": "1",
         "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/8"
                       "3.0.4103.106 Safari/537.36",
     }
     self.session = requests.session()
     self.session.headers = headers

     # 创建web驱动对象 ---> 自动化
     self.driver = webdriver.Chrome()
     self.driver.implicitly_wait(10)
     self.url = url

     # 创建doc文档对象
     self.doc = Document()

     self.run()

     self.driver.quit()
 
 def get_src(self):
     """获取图片父节点"""

     # 向目标网址发起请求、解析出图片url
     # self.driver.get('https://max.book118.com/html/2017/0128/87099242.shtm')
     self.driver.get(self.url)
     self.filename = self.driver.find_element_by_xpath('//*[@id="main"]/div[1]/div[1]/h1').text[:-7] + 'docx'

     # 点击继续浏览
     while True:
         # tag = self.driver.find_element_by_id("btn_preview_remain")
         tag = self.driver.find_element_by_xpath('//div[@class="btns"]')
         if tag.text == '下载文档':
             break
         else:
             self.driver.execute_script("arguments[0].scrollIntoView();", tag)  # 拖动到可见的元素去
             tag.click()

     # 总页数
     page = self.driver.find_element_by_id('pagenumber').text[:-1]

     self.driver.execute_script("var q=document.documentElement.scrollTop=0")
     # 加载图片
     for i in range(1260, int(page) * 1260, 50):
         self.driver.execute_script("window.scrollTo(0, %s)" % str(i))
         time.sleep(0.02)   # 网速不好把值适当调大
     for i in range(1260 * 6, int(page) * 1260, 50):
         self.driver.execute_script("window.scrollTo(0, %s)" % str(i))
         time.sleep(0.035)   # 网速不好把值适当调大

     srcs = self.driver.find_elements_by_xpath('//div[@class="webpreview-item"]')

     return srcs

 def download(self, src):
     """下载图片"""

     # 利用选择器取出src属性值
     url = src.find_element_by_css_selector('img').get_attribute('src')

     # 获取图片
     print(url)
     if url:
         res = self.session.get(url)
         return res
 
 def createword(self, res):
     """创建word"""

     if res is None:
         return

     # 主动捕获异常
     try:
         # 将图片保存
         with open('1.png', 'wb') as f:
             f.write(res.content)

         # width=Inches(6), height=Inches(8) 将写入的图片设置成A4大小
         self.doc.add_picture("1.png", width=Inches(6), height=Inches(8))

     except Exception as e:
         print('1.png 写入失败，原因是：%s' % str(e))

     # 保存成word文档
     self.doc.save(self.filename)
 
 def createpdf(self):
     """word转pdf """

     word = gencache.EnsureDispatch('Word.Application')
     self.doc = word.documents.Open(self.filename, ReadOnly=1)
     self.doc.ExportAsFixedFormat(
         self.pdfPath,
         constants.wdExportFormatPDF,
         Item=constants.wdExportdocumentWithMarkup,
         CreateBookmarks=constants.wdExportCreateHeadingBookmarks
     )
     word.Quit(constants.wdDoNotSaveChanges)
     
 def run(self):
     for src in self.get_src():
         res = self.download(src)
         self.createword(res)
         # self.createpdf()


YuanLC(
 url='https://max.book118.com/html/2021/0106/6232223004003045.shtm',
)

^_^有帮助就给个赞吧~~~

全屏阅览式点这 原版滑动式点这