分享80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 = 96  # 采集数量
    sprider_start_count=5200#
    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"
    filter_down_file=[]
    def __init__(self):
        pass
    def sprider(self,title_name="NET"):
        """
       采集
       PHP https://down.chinaz.com/class/572_5_1.htm
       NET https://down.chinaz.com/class/572_4_1.htm
       ASP https://down.chinaz.com/class/572_3_1.htm
       Python https://down.chinaz.com/class/604_572_1.htm
            https://down.chinaz.com/class/608_572_1.htm
        微信 https://down.chinaz.com/class/610_572_1.htm
       Ruby   https://down.chinaz.com/class/622_572_1.htm
       NodeJs https://down.chinaz.com/class/626_572_1.htm
       C https://down.chinaz.com/class/594_572_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"
        elif title_name == "ASP":
            self.folder_name = "ASP源码"
            self.second_column_name = "572_3"
        elif title_name == "Python":
            self.folder_name = "Python源码"
            self.second_column_name = "604_572"
        elif title_name == "JavaScript":
            self.folder_name = "JavaScript源码"
            self.second_column_name = "602_572"
        elif title_name == "Java":
            self.folder_name = "Java源码"
            self.second_column_name = "572_517"
        elif title_name == "HTML":
            self.folder_name = "HTML-CSS源码"
            self.second_column_name = "608_572"
        elif title_name == "TypeScript":
            self.folder_name = "TypeScript源码"
            self.second_column_name = "772_572"
        elif title_name == "微信小程序":
            self.folder_name = "微信小程序源码"
            self.second_column_name = "610_572"
        elif title_name == "Ruby":
            self.folder_name = "Ruby源码"
            self.second_column_name = "622_572"
        elif title_name == "NodeJs":
            self.folder_name = "NodeJs源码"
            self.second_column_name = "626_572"
        elif title_name == "C++":
            self.folder_name = "C++源码"
            self.second_column_name = "596_572"
        elif title_name == "C":
            self.folder_name = "C源码"
            self.second_column_name = "594_572"
        #https://down.chinaz.com/class/594_572_1.htm
        first_column_name = title_name # 一级目录
        self.sprider_category = title_name  # 一级目录
        second_folder_name = str(self.sprider_count) + "个" + self.folder_name #二级目录
        self.sprider_type =second_folder_name
        self.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=self.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.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(1)

import random
class UserAgent:
    def __init__(self):
        self.headers = [
            "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36",
            "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36",
            "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:30.0) Gecko/20100101 Firefox/30.0",
            "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.75.14 (KHTML, like Gecko) Version/7.0.3 Safari/537.75.14",
            "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; Win64; x64; Trident/6.0)",
            'Mozilla/5.0 (Windows; U; Windows NT 5.1; it; rv:1.8.1.11) Gecko/20071127 Firefox/2.0.0.11',
            'Opera/9.25 (Windows NT 5.1; U; en)',
            'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)',
            'Mozilla/5.0 (compatible; Konqueror/3.5; Linux) KHTML/3.5.5 (like Gecko) (Kubuntu)',
            'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.0.12) Gecko/20070731 Ubuntu/dapper-security Firefox/1.5.0.12',
            'Lynx/2.8.5rel.1 libwww-FM/2.14 SSL-MM/1.4.1 GNUTLS/1.2.9',
            "Mozilla/5.0 (X11; Linux i686) AppleWebKit/535.7 (KHTML, like Gecko) Ubuntu/11.04 Chromium/16.0.912.77 Chrome/16.0.912.77 Safari/535.7",
            "Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:10.0) Gecko/20100101 Firefox/10.0 "
        ]
    def get_random_agent(self):
        randdom_agent = random.choice(self.headers)
        return randdom_agent
        pass
    def get_random_header(self, header_url):
        headers = {"Referer": header_url,
                   'User-Agent': random.choice(self.headers)}
        return headers
        pass

import os
# 查找指定文件夹下所有相同名称的文件
def search_file(dirPath, fileName):
    dirs = os.listdir(dirPath)  # 查找该层文件夹下所有的文件及文件夹，返回列表
    for currentFile in dirs:  # 遍历列表
        absPath = dirPath + '/' + currentFile
        if os.path.isdir(absPath):  # 如果是目录则递归，继续查找该目录下的文件
            search_file(absPath, fileName)
        elif currentFile == fileName:
            print(absPath)  # 文件存在，则打印该文件的绝对路径
            os.remove(absPath)