分享116个PHP源码，总有一款适合您

import os
import shutil
import time
from time import sleep
import requests
from bs4 import BeautifulSoup
from docx import Document
from docx.shared import Inches
from framework.base.BaseFrame import BaseFrame
from sprider.business.DownLoad import DownLoad
from sprider.business.SeleniumTools import SeleniumTools
from sprider.business.SpriderTools import SpriderTools
from selenium import webdriver
from selenium.webdriver.common.by import By
from sprider.model.SpriderEntity import SpriderEntity
from sprider.access.SpriderAccess import SpriderAccess
class HuaJunCode:
    base_url =  "https://down.chinaz.com" # 采集的网址
    save_path = "D:\\Freedom\\Sprider\\ChinaZ\\"
    sprider_count = 126  # 采集数量
    sprider_start_count=3999 # 从第几个序号开始 直接改数量即可 会做除法操作正 正在采集第32页的第16个资源 debug
    word_content_list = []
    folder_name = ""
    page_end_number=0
    max_pager=15 #每页的数量
    haved_sprider_count =0  # 已经采集的数量
    page_count = 1  # 每个栏目开始业务content="text/html; charset=gb2312"
    def __init__(self):
        pass
    def sprider(self,title_name="NET"):
        """
       采集 https://down.chinaz.com/class/572_5_1.htm
       NET https://down.chinaz.com/class/572_4_1.htm
       :return:
       """
        if title_name == "PHP":
            self.folder_name = "PHP源码"
            self.second_column_name = "572_5"
        elif title_name == "Go":
            self.folder_name = "Go源码"
            self.second_column_name = "606_572"
        elif title_name == "NET":
            self.folder_name = "NET源码"
            self.second_column_name = "572_4"
        first_column_name = title_name # 一级目录
        second_folder_name = str(self.sprider_count) + "个" + self.folder_name #二级目录
        merchant=int(self.sprider_start_count) //int(self.max_pager)+1 #起始页码用于效率采集
        self.file_path = self.save_path + os.sep + "Code" + os.sep + first_column_name + os.sep + second_folder_name
        self.save_path = self.save_path+ os.sep + "Code" + os.sep+first_column_name+os.sep + second_folder_name+ os.sep + self.folder_name
        BaseFrame().debug("开始采集ChinaZCode"+self.folder_name+"...")
        sprider_url = (self.base_url + "/class/{0}_1.htm".format(self.second_column_name))
        down_path="D:\\Freedom\\Sprider\\ChinaZ\\Code\\"+first_column_name+"\\"+second_folder_name+"\\Temp\\"
        if os.path.exists(down_path) is True:
            shutil.rmtree(down_path)
        if os.path.exists(down_path) is False:
            os.makedirs(down_path)
        if os.path.exists(self.save_path ) is True:
            shutil.rmtree(self.save_path )
        if os.path.exists(self.save_path ) is False:
            os.makedirs(self.save_path )
        chrome_options = webdriver.ChromeOptions()
        diy_prefs ={'profile.default_content_settings.popups': 0,
                    'download.default_directory':'{0}'.format(down_path)}
        # 添加路径到selenium配置中
        chrome_options.add_experimental_option('prefs', diy_prefs)
        #chrome_options.add_argument('--headless') #隐藏浏览器
        # 实例化chrome浏览器时，关联忽略证书错误
        driver = webdriver.Chrome(options=chrome_options)
        driver.set_window_size(1280, 800)  # 分辨率 1280*800
        # driver.get方法将定位在给定的URL的网页，get接受url可以是任何网址，此处以百度为例
        driver.get(sprider_url)
        # content = driver.page_source
        # print(content)
        div_elem = driver.find_element(By.CLASS_NAME, "main")  # 列表页面 核心内容
        element_list = div_elem.find_elements(By.CLASS_NAME, 'item')
        laster_pager_ul = driver.find_element(By.CLASS_NAME, "el-pager")
        laster_pager_li =laster_pager_ul.find_elements(By.CLASS_NAME, 'number')
        laster_pager_url = laster_pager_li[len(laster_pager_li) - 1]
        page_end_number = int(laster_pager_url.text)
        self.page_count=merchant
        while self.page_count <= int(page_end_number):  # 翻完停止
            try:
                if self.page_count == 1:
                    self.sprider_detail(driver,element_list,self.page_count,page_end_number,down_path)
                    pass
                else:
                    if self.haved_sprider_count == self.sprider_count:
                        BaseFrame().debug("采集到达数量采集停止...")
                        BaseFrame().debug("开始写文章...")
                        self.builder_word(self.folder_name, self.save_path, self.word_content_list)
                        BaseFrame().debug("文件编写完毕，请到对应的磁盘查看word文件和下载文件！")
                        break
                    #(self.base_url + "/sort/{0}/{1}/".format(url_index, self.page_count))
                    #http://soft.onlinedown.net/sort/177/2/
                    next_url = self.base_url + "/class/{0}_{1}.htm".format(self.second_column_name, self.page_count)
                    driver.get(next_url)
                    div_elem = driver.find_element(By.CLASS_NAME, "main")  # 列表页面 核心内容
                    element_list = div_elem.find_elements(By.CLASS_NAME, 'item')
                    self.sprider_detail( driver, element_list, self.page_count, page_end_number, down_path)
                    pass
                #print(self.page_count)
                self.page_count = self.page_count + 1  # 页码增加1
            except Exception as e:
                print("sprider()执行过程出现错误:" + str(e))
                sleep(10)