分享48个Go源码，总有一款适合您

import os
from time import sleep
import requests
from bs4 import BeautifulSoup
from docx import Document
from docx.shared import Inches
from framework.access.sprider.SpriderAccess import SpriderAccess
from framework.base.BaseFrame import BaseFrame
from framework.pulgin.Tools import Tools
from sprider.business.DownLoad import DownLoad
from sprider.model.SpriderEntity import SpriderEntity
from sprider.business.SpriderTools import SpriderTools
from sprider.business.UserAgent import UserAgent
class ChinaZCode:
    page_count = 1  # 每个栏目开始业务content="text/html; charset=gb2312"
    base_url = "https://down.chinaz.com"  # 采集的网址  https://sc.chinaz.com/tag_ppt/zhongguofeng.html
    save_path = "D:\\Freedom\\Sprider\\ChinaZ\\"
    sprider_count = 66 # 采集数量
    haved_sprider_count = 0  # 正在采集第429页的第15个资源共499页资源 正在采集第208页的第12个资源共499页资源
    word_content_list = []
    folder_name = ""
    first_column_name = "PHP"
    sprider_start_count=0 #已经采集完成第136个 debug
    max_pager=16 #每页的数量
    # 如果解压提升密码错误 ，烦请去掉空格。如果还是不行烦请下载WinRAR
    # https: // www.yadinghao.com / file / 393740984E6754
    # D18635BF2DF0749D87.html
    # 此压缩文件采用WinRAR压缩。
    # 此WinRAR是破解版。
    def __init__(self):
        #A5AndroidCoder().sprider("android", "youxi", 895)  #
        pass
    def sprider(self, title_name="Go"):
        """
        采集 https://down.chinaz.com/class/572_5_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"
        merchant = int(self.sprider_start_count) // int(self.max_pager) + 1
        second_folder_name = str(self.sprider_count) + "个" + self.folder_name
        self.save_path = self.save_path+ os.sep + "Code" + os.sep +  second_folder_name
        print("开始采集ChinaZCode"+self.folder_name+"...")
        sprider_url = (self.base_url + "/class/{0}_1.htm".format(self.second_column_name))
        #print(sprider_url)
        #sprider_url = (self.base_url + "/" +  self.first_column_name + "/" + second_column_name + ".html")
        response = requests.get(sprider_url, timeout=10, headers=UserAgent().get_random_header(self.base_url))
        response.encoding = 'UTF-8'
        soup = BeautifulSoup(response.text, "html5lib")
        #print(soup)
        div_list =soup.find('div', attrs={"class": 'main'})
        div_list=div_list.find_all('div', attrs={"class": 'item'})
        #print(div_list)
        laster_pager_ul = soup.find('ul', attrs={"class": 'el-pager'})
        laster_pager_li = laster_pager_ul.find_all('li', attrs={"class": 'number'})
        laster_pager_url = laster_pager_li[len(laster_pager_li)-1]
        #<a href="zhongguofeng_89.html"><b>89</b></a>
        page_end_number = int(laster_pager_url.string)
        #print(page_end_number)
        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(div_list,self.page_count,page_end_number)
                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
                    next_url =self.base_url + "/class/{0}_{1}.htm".format(self.second_column_name,self.page_count )
                    response = requests.get(next_url, timeout=10, headers=UserAgent().get_random_header(self.base_url))
                    response.encoding = 'UTF-8'
                    soup = BeautifulSoup(response.text, "html5lib")
                    div_list = soup.find('div', attrs={"class": 'main'})
                    div_list = div_list.find_all('div', attrs={"class": 'item'})
                    self.sprider_detail(div_list, self.page_count,page_end_number)
                    pass
            except Exception as e:
                print("sprider()执行过程出现错误" + str(e))
                pass
            self.page_count = self.page_count + 1  # 页码增加1
    def sprider_detail(self, element_list, page_count,max_page):
        try:
            element_length = len(element_list)
            self.sprider_start_index = int(self.sprider_start_count) % int(self.max_pager)
            index = self.sprider_start_index
            while index < element_length:
                a=element_list[index]
                if self.haved_sprider_count == self.sprider_count:
                    BaseFrame().debug("采集到达数量采集停止...")
                    break
                index = index + 1
                sprider_info = "正在采集第" + str(page_count) + "页的第" + str(index) + "个资源共"+str(max_page)+"页资源"
                print(sprider_info)
                #title_image_obj = a.find('img', attrs={"class": 'lazy'})
                url_A_obj=a.find('a', attrs={"class": 'name-text'})
                next_url = self.base_url+url_A_obj.get("href")
                coder_title = url_A_obj.get("title")
                response = requests.get(next_url, timeout=10, headers=UserAgent().get_random_header(self.base_url))
                response.encoding = 'UTF-8'
                soup = BeautifulSoup(response.text, "html5lib")
                #print(soup)
                down_load_file_div = soup.find('div', attrs={"class": 'download-list'})
                if down_load_file_div is None:
                    BaseFrame().debug("应该是多版本的暂时不下载因此跳过哦....")
                    continue
                down_load_file_url =self.base_url+down_load_file_div.find('a').get("href")
                #image_obj = soup.find('img', attrs={"class": "el-image__inner"})
                #image_src =self.base_url+image_obj.get("src")
                #print(image_src)
                codeEntity = SpriderEntity()  # 下载过的资源不再下载
                codeEntity.sprider_base_url = self.base_url
                codeEntity.create_datetime = SpriderTools.get_current_datetime()
                codeEntity.sprider_url = next_url
                codeEntity.sprider_pic_title = coder_title
                codeEntity.sprider_pic_index = str(index)
                codeEntity.sprider_pager_index = page_count
                codeEntity.sprider_type = "code"
                if SpriderAccess().query_sprider_entity_by_urlandindex(next_url, str(index)) is None:
                    SpriderAccess().save_sprider(codeEntity)
                else:
                    BaseFrame().debug(coder_title + next_url + "数据采集过因此跳过")
                    continue
                if (DownLoad(self.save_path).down_load_file__(down_load_file_url, coder_title, self.folder_name)):
                    #DownLoad(self.save_path).down_cover_image__(image_src, coder_title)  # 资源的 封面
                    sprider_content = [coder_title,
                                       self.save_path + os.sep + "image" + os.sep + coder_title + ".jpg"]  # 采集成功的记录
                    self.word_content_list.append(sprider_content)  # 增加到最终的数组
                    self.haved_sprider_count = self.haved_sprider_count + 1
                    BaseFrame().debug("已经采集完成第" + str(self.haved_sprider_count) + "个")
            if (int(page_count) == int(max_page)):
                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！")
        except Exception as e:
            print("sprider_detail:" + str(e))
            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)