【python】课堂派爬虫禁止下载的ppt

先爬取pdf中所有的图片，下载到本地

注意：下面程序，方法可以不看，但是要先在main函数里把账号密码啥的改成你自己的。

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2022/12/1 8:41
# @Author  : Fw_022
import time

"""
获取网页源码
request--get
"""


def get(url):
    import requests  # 导入requests包

    html = requests.get(url)  # Get方式获取网页数据
    text = html.text  # 获得html（整个网页）的源码部分
    return text


"""
F12，单击"Network"
对页面进行操作
开发者模式中，依次单击“Network”按钮和“XHR”按钮，找到目标数据。
将 Headers 中的 URL 复制出来
"""


def make_folder(folder_path):
    import os
    if not os.path.exists(folder_path):
        os.makedirs(folder_path)
    return folder_path


# url 必须是headers的，不是原网址
def post(url):
    import json
    import requests  # 导入requests包

    From_data = {'i': "word", 'from': 'zh-CHS', 'to': 'en', 'smartresult': 'dict', 'client': 'fanyideskweb',
                 'salt': '15477056211258', 'sign': 'b3589f32c38bc9e3876a570b8a992604', 'ts': '1547705621125',
                 'bv': 'b33a2f3f9d09bde064c9275bcb33d94e', 'doctype': 'json', 'version': '2.1', 'keyfrom': 'fanyi.web',
                 'action': 'FY_BY_REALTIME', 'typoResult': 'false'}
    response = requests.post(url, data=From_data)  # 请求表单数据
    content = json.loads(response.text)  # 将Json格式字符串转字典
    print(content)


def beautifulsoup(url):
    import requests  # 导入requests包
    from bs4 import BeautifulSoup
    html = requests.get(url)
    soup = BeautifulSoup(html.text, 'lxml')
    """
    :method soup.select()，
    :return list
    
    标签名 不加任何修饰
    类名  .
    id #
    """
    data = soup.select('img')
    for i in data:
        print(i)


class Beautiful():

    def __init__(self, url, account, password):
        self.url = url
        self.web = None
        self.account = account
        self.password = password
        self.start()
        time.sleep(5)
        self.start2()
        time.sleep(3)

    def start(self):
        from selenium import webdriver
        from selenium.webdriver.chrome.service import Service

        web = webdriver.Chrome(service=Service(r"C:\Program Files\Google\Chrome\Application\chromedriver.exe"))
        web.implicitly_wait(5)
        web.get(self.url)
        self.web = web
        self.input('/html/body/div/div[2]/div[2]/div[2]/div/div/form/div[1]/div/div/input', self.account)
        self.input('/html/body/div/div[2]/div[2]/div[2]/div/div/form/div[2]/div/div/input', self.password)
        print("登陆成功")

    def start2(self):
        self.web.get(self.url)
        print("到达网页")

    def get_form_xpath(self, xpath):
        from selenium.webdriver.common.by import By
        data = self.web.find_element(By.XPATH, xpath)
        return data

    def get_from_class(self, class_name):
        from selenium.webdriver.common.by import By
        data = self.web.find_element(By.CLASS_NAME, class_name)
        return data

    def get_src(self, element):
        img = element.get_attribute('src')
        return img

    def save_img(self, save_path, img_url):
        if img_url == None:
            return
        import requests  # 导入requests包
        img = requests.get(img_url)
        file = open(save_path, "wb")
        file.write(img.content)
        file.close()

    def input(self, xpath, string):
        data = self.get_form_xpath(xpath)
        data.clear()
        data.send_keys(string)


if __name__ == "__main__":
    # 所有需要设置的参数：想要爬取的pdf的url,总页码数page,保存路径path,账号,密码
    url = "xxx"
    page = 45
    path = make_folder("xxx")
    account, password = "xxx", "xxx"

    bea = Beautiful(url,account,password)
    # 注意这里从1开始，因为i代表页码
    for i in range(1, page + 1):
        pic_xpath = "/html/body/div/div[2]/div[1]/div/div[1]/div[2]/img"
        title_xpath = "/html/body/div/div[2]/div[1]/div/div[1]/div[1]/p"
        page_input_xpath = "/html/body/div/div[2]/div[2]/aside/div[2]/div/input"

        # 到达页面（输入页码后，点击任意一个地方，这里设置为点击标题）
        bea.input(page_input_xpath, str(i))
        bea.get_form_xpath(title_xpath).click()

        # 获取图片
        data = bea.get_form_xpath(pic_xpath)
        img = bea.get_src(data)
        print("===> 找到图片" + str(i))

        # 保存图片
        save = path + "\\" + str(i) + ".jpg"
        bea.save_img(save, img)
        print("保存到路径" + save + "\n")

将爬取的图片合成pdf

也是一样的，在main函数里修改自己的参数

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2022/12/1 14:16
# @Author  : Fw_022
import img2pdf
import os
import re


def make_folder(folder_path):
    import os
    if not os.path.exists(folder_path):
        os.makedirs(folder_path)
    return folder_path


def from_photo_to_pdf(photo_path, width, height):
    # 0、保存地址为：pdf/图片文件夹.pdf
    save_path = make_folder(r"pdf/" + photo_path) + ".pdf"

    # 1、按名称排序，注意这里按照数字排序，而不是字典序。否则会出现乱序
    new_list = os.listdir(photo_path)
    new_list = [os.path.join(photo_path, i) for i in new_list]
    new_list.sort(key=lambda x: int(re.findall(r'\d+', x)[0]))
    print(new_list)

    # 2、指定pdf的单页的宽和高
    a4inpt = (img2pdf.mm_to_pt(width), img2pdf.mm_to_pt(height))
    layout_fun = img2pdf.get_layout_fun(a4inpt)
    with open(save_path, 'wb') as f:
        f.write(img2pdf.convert(new_list, layout_fun=layout_fun))


if __name__ == '__main__':
    photo_path = "xxx"
    width, height = 720, 540
    from_photo_to_pdf(photo_path, width, height)