# @author: zly

# @copyright: all right reversed

# @time: 2020-09-07

# @function: Download payment principle create website document

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 gencache

from win32com.client import constants, gencache

def createword():

# 创建doc文档对象

doc = Document()

# 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,application/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%3E1599561968279953439%7C%7C%7Cfsts%3D%3E1599561968%7C%7C%7Cdsfs%3D%3E0%7C%7C%7Cnps%3D%3E1; s_s=cdh%3D%3E27a30245%7C%7C%7Clast_req%3D%3E1599561968%7C%7C%7Csid%3D%3E1599561968685697441%7C%7C%7Cdsps%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/83.0.4103.106 Safari/537.36",

}

session = requests.Session()

session.headers = headers

# 创建web驱动对象 自动化

driver = webdriver.Chrome()

driver.implicitly_wait(10)

# 向目标网址发起请求、解析出图片url

driver.get('https://max.book118.com/index.php?g=Home&m=NewView&a=index&aid=8103000063001125&v=20200819')

for i in range(1, 45):

# 一定要两个退格，因为两位数时需要退格两次

driver.find_element_by_xpath('//*[@id="newView"]/div[1]/div/input').send_keys(keys.Keys.BACK_SPACE, keys.Keys.BACK_SPACE, i, keys.Keys.ENTER)

# 等待图片加载时间 10s

time.sleep(10)

# 利用选择器取出src属性值

src = driver.find_element_by_xpath('//div[@class="webpreview-item"][%s]' % i).find_element_by_css_selector('img').get_attribute('src')

# 获取图片

res = session.get(src)

# 主动捕获异常

try:

# 将图片保存

with open('%s.png' % i, '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

doc.add_picture('%s.png' % i, width=Inches(6), height=Inches(8))

print('%s.png 写入成功' % i)

except Exception as e:

print('%s.png 写入失败，原因是：%s' % (i, str(e)))

# 保存成word文档，命名为 学术英语.docx

doc.save("学术英语.docx")

driver.quit()

def createpdf(wordPath, pdfPath):

"""

word转pdf

@wordPath: word文件路径

@pdfPath: 生成pdf文件路径

"""

word = gencache.EnsureDispatch('Word.Application')

doc = word.Documents.Open(wordPath, ReadOnly=1)

doc.ExportAsFixedFormat(

pdfPath,

constants.wdExportFormatPDF,

Item=constants.wdExportDocumentWithMarkup,

CreateBookmarks=constants.wdExportCreateHeadingBookmarks

)

word.Quit(constants.wdDoNotSaveChanges)

createword()

createpdf("学术英语.docx", "学术英语.pdf")