Python3网络爬虫：网易新闻App的广告数据抓取

咱们就不说废话了，直接上完整的源码

def startGetData(self):self.url = "https://nex.163.com/q"
    body = self.getBody()self.parse_url(self.url, body)

这个是启动函数

def getBody(self):body = """{
   "adunit": {
      "category": "FOCUS2",
      "app_version": "34.0",
      "city": "",
      "app": "7A16FBB6",
      "location": "1,2,20,21,22,23,24,25,26,27,28,29,30,31,10",
      "blacklist": "",
      "province": ""
   },
   "ext_param": {},
   "device": {
      "mac": "",
      "dt": "iPhone 6",
      "idfa": "18454932-A441-4720-8973-776284A58B7F",
      "mcc": "",
      "longitude": "113.3360799435621",
      "isp": "cm",
      "latitude": "23.12629215782341",
      "dq": "750x1334",
      "os": "ios",
      "imei": "",
      "galaxy_tag": "C622E64A-3478-40E6-99EC-32AB80BE4D4B",
      "city_code": "440106",
      "network_status": "wifi",
      "location_type": 1,
      "udid": ""
   },
   "version": "9.1.3",
   "urs": "2qq2Z9GdG9+N5ruzJyW1p8aKM2B+F3Tmv+EBsxR5PT4=",
   "is_test": false
}"""
        return body；这个是接口需要携带的参数

def parse_url(self, url, body):response = requests.post(url, data=body, verify=False
    self.parse_json(response.content.decode("utf-8"))//网络请求并返回json字符窜

def parse_json(self, jsonStr):DataInfo.time = Util().getCurrTime()try:json_list = (json.loads(jsonStr))["ads"]for json_str in json_list:adid = json_str["adid"]if adid.startswith("yx"):self.savaDataInfo(json_str)except KeyError as x:print(x)

解析json数据并筛选游戏广告

def savaDataInfo(self, json_str):DataInfo.title = json_str["title"]DataInfo.type = 1
    DataInfo.channel = "wangyixinwen"
    DataInfo.appdownload = json_str["relatedActionLinks"][0]["url"]self.saveBitmapOrPath(json_str)DataInfo.device_type = "ios"
    DataInfo.source_type = 1
    MySqlManager().insert_inspection_list(4)

将广告数据保存到mysql数据库

def saveBitmapOrPath(self, json_str):bitmap = {}bitmap_path = {}filename = "pic1_" + str(int(time.time() * 1000000)) + ".jpg"
    bitmap_path["pic_path1"] = self.path + filenameDataInfo.pic_path = bitmap_pathbitmap["pic1"] = json_str["resources"][0]["urls"][0]Util().save_img(bitmap["pic1"], filename, self.path)DataInfo.pic_list = bitmap

将游戏广告图片下载到服务器

def getFilePath(self, plat):return "/upload/" + plat + "/" + str(time.strftime("%Y-%m") + "/")def save_img(self, limg_url, filename, path):# 保存图片到磁盘文件夹 file_path中，默认为当前脚本运行目录下的 book\img文件夹
    try:file_path = "/home/tianchao/python/materialscript" + pathif not os.path.exists(file_path):print('文件夹', file_path, '不存在，重新建立')os.makedirs(file_path)pic = requests.get(limg_url, timeout=5)  # 超时异常判断 5秒超时
        file_name = file_path + filenameprint(file_name)fp = open(file_name, 'wb')fp.write(pic.content)  # 写入图片
        fp.close()except IOError as e:print('文件操作失败:', e)except Exception as e:print('错误 ：', e)

保存图片代码

def __init__(self):self.product_detail = "product_detail"
    self.path = Util().getFilePath("dataeye")self.pic1_path = ""
    self.pic2_path = ""
    self.pic3_path = ""
    try:self.conn = pymysql.connect(host='123.207.58.110',
                                    port=3306,
                                    user='root',
                                    password='iwkSlb0yt=pu',
                                    db="material_database",
                                    charset='utf8',
                                    cursorclass=pymysql.cursors.DictCursor)except OperationalError as e:print(e)# 将产品详情插入数据库
def insert_product_detail(self, product_id, json_obj):table_name = "product_detail"
    if self.isProductIdExits(table_name, product_id) == 1:update_sql = "UPDATE " + table_name + " SET company_num=%d,days=%d,first_seen='%s',labels='%s',last_seen='%s'," \"logo_url='%s',media_list='%s',media_num=%d,product_id=%d,product_name='%s',updated_at='%s' WHERE product_id=%d" \% (json_obj["companyNum"], json_obj["days"], json_obj["firstSeen"], json_obj["labels"],
                        json_obj["lastSeen"], json_obj["logoURL"],
                        json.dumps(json_obj["mediaList"]), json_obj["mediaNum"], json_obj["productId"],
                        json_obj["productName"], self.getCurrentTime(), product_id)self.execute(update_sql)else:insert_sql = "INSERT INTO " + table_name + "(company_num,days,first_seen,labels,last_seen,logo_url,media_list,media_num,product_id,product_name,created_at)" \" VALUES (%d ,%d ,'%s','%s','%s','%s','%s',%d ,%d ,'%s','%s')" \% (json_obj["companyNum"], json_obj["days"], json_obj["firstSeen"], json_obj["labels"],
                        json_obj["lastSeen"], json_obj["logoURL"],
                        json.dumps(json_obj["mediaList"]), json_obj["mediaNum"], json_obj["productId"],
                        json_obj["productName"], self.getCurrentTime())self.execute(insert_sql)# 将产品详情页图标数据插入数据库
def insert_product_detail_table(self, product_id, json_obj):table_name = "product_detail_table"
    if self.isProductIdExits(table_name, product_id) == 1:update_sql = "UPDATE " + table_name + " SET ad_creative_list='%s',ad_creative_list='%s',xlabel='%s',ad_count_last_year=%d,product_id=%d,updated_at='%s' WHERE product_id=%d" \% (json.dumps(json_obj["adCreativeList"]), json.dumps(json_obj["adMaterialList"]),
                        json.dumps(json_obj["xlabel"]), json_obj["adCountLastYear"],
                        product_id, self.getCurrentTime(), product_id)self.execute(update_sql)else:insert_sql = "INSERT INTO " + table_name + "(ad_creative_list,ad_material_list,xlabel,ad_count_last_year,product_id,created_at)" \" VALUES ('%s','%s','%s',%d,%d,'%s')" \% (json.dumps(json_obj["adCreativeList"]), json.dumps(json_obj["adMaterialList"]),
                         json.dumps(json_obj["xlabel"]), json_obj["adCountLastYear"],
                         product_id, self.getCurrentTime())self.execute(insert_sql)# 将图片素材插入数据库
def insert_product_detail_pic(self, product_id, json_obj):self.savePic(json_obj)table_name = "product_pic_material_list"
    material_id = json_obj["materialId"]if self.isMaterialIdExits(table_name, material_id) == 1:update_sql = "UPDATE " + table_name + " SET company_num=%d,creative_num=%d,first_seen='%s',h=%d,last_days=%d,last_seen='%s',material_id=%d,material_type=%d," \"media_list='%s',new='%s',pic1='%s',pic2='%s',pic3='%s',product_num=%d,video='%s',w=%d,product_id=%d,video='%s' WHERE material_id=%d" \% (json_obj["companyNum"], json_obj["creativeNum"], json_obj["firstSeen"], json_obj["h"],
                        json_obj["lastDays"], json_obj["lastSeen"], material_id,
                        json_obj["materialType"],
                        json.dumps(json_obj["mediaList"]), json_obj["new"], json_obj["pic1"], json_obj["pic2"],
                        json_obj["pic3"],
                        json_obj["productNum"], json_obj["video"], json_obj["w"], product_id,
                        self.getCurrentTime(), material_id)self.execute(update_sql)else:insert_sql = "INSERT INTO " + table_name + "(company_num,creative_num,first_seen,h,last_days,last_seen,material_id,material_type,media_list,new,pic1,pic2,pic3" \",product_num,video,w,product_id,created_at,pic1_path,pic2_path,pic3_path)" \" VALUES (%d,%d,'%s',%d,%d,'%s',%d,%d,'%s','%s','%s','%s','%s',%d,'%s',%d,%d,'%s','%s','%s','%s')" \% (json_obj["companyNum"], json_obj["creativeNum"], json_obj["firstSeen"], json_obj["h"],
                         json_obj["lastDays"], json_obj["lastSeen"], json_obj["materialId"],
                         json_obj["materialType"],
                         json.dumps(json_obj["mediaList"]), json_obj["new"], json_obj["pic1"], json_obj["pic2"],
                         json_obj["pic3"],
                         json_obj["productNum"], json_obj["video"], json_obj["w"], product_id,
                         self.getCurrentTime(), self.pic1_path, self.pic2_path, self.pic3_path)self.execute(insert_sql)def savePic(self, json_obj):pic1 = json_obj["pic1"]pic2 = json_obj["pic2"]pic3 = json_obj["pic3"]if pic1.strip() != '':filename = "pic1_" + str(int(time.time() * 1000000)) + ".jpg"
        self.pic1_path = self.path + filenameUtil().save_img(pic1, filename, self.path)if pic2.strip() != '':filename = "pic2_" + str(int(time.time() * 1000000)) + ".jpg"
        self.pic2_path = self.path + filenameUtil().save_img(pic2, filename, self.path)if pic3.strip() != '':filename = "pic3_" + str(int(time.time() * 1000000)) + ".jpg"
        self.pic3_path = self.path + filenameUtil().save_img(pic3, filename, self.path)def isProductIdExits(self, table_name, product_id):query_sql = "select *from " + table_name + " where product_id = " + str(product_id)cursor = self.conn.cursor()result = cursor.execute(query_sql)print(result)self.conn.commit()return resultdef isMaterialIdExits(self, table_name, material_id):query_sql = "select *from " + table_name + " where material_id = " + str(material_id)cursor = self.conn.cursor()result = cursor.execute(query_sql)print(result)self.conn.commit()return resultdef insert_inspection_list(self, table_id):sql = "INSERT INTO " + self.getTableName(table_id) + "(title,app_download,time,channel,type,content,gif,video,source_type,pic_list,pic_path,device_type,material_size,app_name,created_at,updated_at)" \" VALUES ('%s','%s','%s','%s',%d,'%s','%s','%s',%d,'%s','%s','%s','%s','%s','%s','%s')" \% (DataInfo.title, DataInfo.app_download, DataInfo.time, DataInfo.channel, DataInfo.type,
             DataInfo.content, json.dumps(DataInfo.gif), json.dumps(DataInfo.video), DataInfo.source_type,
             json.dumps(DataInfo.pic_list),
             json.dumps(DataInfo.pic_path), DataInfo.device_type,
             DataInfo.material_size,
             DataInfo.app_name, self.getCurrentTime(), self.getCurrentTime())cursor = self.conn.cursor()cursor.execute(sql)self.conn.commit()def getCurrentTime(self):return str(time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time())))def getTableName(self, table_id):return "material_" + str(table_id % 10)def execute(self, sql):cursor = self.conn.cursor()cursor.execute(sql)self.conn.commit()def close(self):self.conn.close()

保存数据库代码

这里把爬取网易平台新闻和广告的代码贡献出来，希望可以帮到大家

Python3网络爬虫：网易新闻App的广告数据抓取相关推荐

Python3网络爬虫之Scrapy框架实现招聘数据抓取
项目需求: 某招聘网上面有公司发布的的各种工作岗位,进入首页 https://careers.tencent.com/ 后可见到一个搜索框,如下图所示: 在搜索框输入岗位名称,跳转到如下图所示页面, ...
Python3网络爬虫：腾讯新闻App的广告数据抓取
废话就不说了,咱们直接上代码 def startGetData(self):index = 0while index < 3:index = index + 1self.url = " ...
Python3网络爬虫：今日头条新闻App的广告数据抓取
咱们就不说废话了,直接上完整的源码 def startGetData(self):ret = random.randint(2, 10)index = 0 url = "" whi ...
Python3网络爬虫实战-38、动态渲染页面抓取:Splash的使用
Splash 是一个 JavaScript 渲染服务,是一个带有 HTTP API 的轻量级浏览器,同时它对接了 Python 中的 Twisted和 QT 库,利用它我们同样可以实现动态渲染页面的抓 ...
Python3网络爬虫实战-27、Requests与正则表达式抓取猫眼电影排行
本节我们利用 Requests 和正则表达式来抓取猫眼电影 TOP100 的相关内容,Requests 相较于 Urllib 使用更加方便,而目前我们还没有系统学习 HTML 解析库,所以可能对 HT ...
【Python】Python3网络爬虫实战-27、Requests与正则表达式抓取猫眼电影排行
本节我们利用 Requests 和正则表达式来抓取猫眼电影 TOP100 的相关内容,Requests 相较于 Urllib 使用更加方便,而目前我们还没有系统学习 HTML 解析库,所以可能对 HT ...
Python爬虫入门实战之猫眼电影数据抓取(理论篇)
前言本文可能篇幅较长,但是绝对干货满满,提供了大量的学习资源和途径.达到让读者独立自主的编写基础网络爬虫的目标,这也是本文的主旨,输出有价值能够真正帮助到读者的知识,即授人以鱼不如授人以渔,让我们直 ...
python编程理论篇_Python爬虫入门实战之猫眼电影数据抓取(理论篇)
前言本文可能篇幅较长,但是绝对干货满满,提供了大量的学习资源和途径.达到让读者独立自主的编写基础网络爬虫的目标,这也是本文的主旨,输出有价值能够真正帮助到读者的知识,即授人以鱼不如授人以渔,让我们直 ...
python爬虫入门实战争胜法_Python爬虫入门实战之猫眼电影数据抓取(理论篇)
前言本文可能篇幅较长,但是绝对干货满满,提供了大量的学习资源和途径.达到让读者独立自主的编写基础网络爬虫的目标,这也是本文的主旨,输出有价值能够真正帮助到读者的知识,即授人以鱼不如授人以渔,让我们直 ...

Python3网络爬虫：网易新闻App的广告数据抓取

Python3网络爬虫：网易新闻App的广告数据抓取相关推荐

最新文章

热门文章