前言:
如今兄弟们对“python爬虫淘宝mm”大致比较着重,咱们都需要知道一些“python爬虫淘宝mm”的相关知识。那么小编在网上汇集了一些关于“python爬虫淘宝mm””的相关文章,希望你们能喜欢,朋友们快快来了解一下吧!前言
Python爬取淘宝美女信息下载本地并同时存储mysql数据库,存储数据库用到了pymysql模块,sql语句简单好用,直接上代码,源码请点链接Python-Spiders文集。
项目结构:
本地存储,判断文件和文件夹是否存在,不存在继续下载
存储mysql数据库,pymysql模块链接数据库,用游标对象来操作数据库,判断数据库是否存在改数据,不存在就插入,存在就跳过
代码展示
from urllib import request, parse, errorimport jsonimport osimport pymysqlimport ssl'''这是小编准备的python爬虫学习资料,加群:821460695 即可免费获取!'''# 请求链接需要设置ssl认证ssl._create_default_https_context = ssl._create_unverified_contextclass TaoBao(): def __init__(self): # 设置头部 self.headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36'} # 设置get参数 self.params = {'_input_charset': 'utf-8', 'q': '', 'viewFlag': 'A', 'sortType': 'default', 'searchStyle': '', 'searchRegion': 'city', 'searchFansNum': '', 'currentPage': '', 'pageSize': '20' } self.url = '' def get_connect(self): self.tablename = 'taobao' self.db = pymysql.connect(host='127.0.0.1', user='root', passwd='', db='test', charset='utf8') self.cur = self.db.cursor() self.cur.execute('USE test') try: # 创建表 self.cur.execute('CREATE TABLE '+self.tablename+' (id BIGINT(7) NOT NULL AUTO_INCREMENT, name VARCHAR(100), city VARCHAR(20), height VARCHAR(10), weight VARCHAR(10), homepage VARCHAR(100), profile VARCHAR(100), pic VARCHAR(100), created TIMESTAMP DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY(id))') except pymysql.err.InternalError as e: print(e) # 修改表字段 self.cur.execute('ALTER DATABASE test CHARACTER SET = utf8mb4 COLLATE = utf8mb4_unicode_ci') self.cur.execute('ALTER TABLE '+self.tablename+' CONVERT TO CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci') self.cur.execute('ALTER TABLE '+self.tablename+' CHANGE name name VARCHAR(100) CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci') self.cur.execute('ALTER TABLE '+self.tablename+' CHANGE city city VARCHAR(20) CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci') self.cur.execute('ALTER TABLE '+self.tablename+' CHANGE height height VARCHAR(10) CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci') self.cur.execute('ALTER TABLE '+self.tablename+' CHANGE weight weight VARCHAR(10) CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci') self.cur.execute('ALTER TABLE '+self.tablename+' CHANGE homepage homepage VARCHAR(100) CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci') self.cur.execute('ALTER TABLE '+self.tablename+' CHANGE profile profile VARCHAR(100) CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci') self.cur.execute('ALTER TABLE '+self.tablename+' CHANGE pic pic VARCHAR(100) CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci') def insert_table(self,name, city, height, weight, hompage, profile, pic): self.cur.execute('INSERT INTO '+self.tablename+' (name, city, height, weight, homepage, profile, pic) VALUES (\"%s\", \"%s\", \"%s\", \"%s\", \"%s\", \"%s\", \"%s\")', (name, city, height, weight, hompage, profile, pic)) self.cur.connection.commit() def get_html(self,page): self.params['currentPage'] = str(page) # urlencode可以把字典=键值对编码成url地址中get参数 self.param = parse.urlencode(self.params).encode('utf-8') # data=self.param 上传参数 req = request.Request(self.url, data=self.param, headers=self.headers) content = request.urlopen(req) content = json.loads(content.read().decode('gbk')) if content['status'] == -1: return -1 return content def parser_json(self,content, page): meinvist = [] # 解析json数据 data = content['data']['searchDOList'] for list in data: temp = {} temp['id'] = str(list['userId']) temp['name'] = list['realName'] temp['city'] = list['city'] temp['height'] = str(list['height']) temp['weight'] = str(list['weight']) temp['favornum'] = str(list['totalFavorNum']) temp['profile'] = 'http:'+list['avatarUrl'] temp['pic'] = 'http:'+list['cardUrl'] # meinvist.append(temp) self.mkdir(temp['name']) print('%s正在抓取%s'%(page, temp['name'])) self.get_img(temp['profile'], temp['name'], 'profile') self.get_img(temp['pic'], temp['name'], 'pic') if not os.path.exists('./'+temp['name']+'/info.txt'): with open('./'+temp['name']+'/info.txt', 'w') as f: f.write(temp['name']+'\n') f.write(temp['city']+'\n') f.write(temp['height']+'\n') f.write(temp['weight']+'\n') # 插入数据库 self.insert_table(temp['name'], temp['city'], temp['height'], temp['weight'], ''+temp['id'], temp['profile'], temp['pic']) # return meinvist # 判断文件夹是否存在 def mkdir(self,path): if not os.path.exists(path): os.makedirs(path) else: print('目录已存在!') # 判断文件是否存在 def get_img(self,url, path, name): if os.path.exists('./' + path + '/' + name + '.jpg'): print('文件已存在!') return 0 try: req = request.Request(url, headers=self.headers) reponse = request.urlopen(req) get_img = reponse.read() with open('./' + path + '/' + name + '.jpg', 'wb') as fp: fp.write(get_img) # 也可以用一下代码实现图片的下载 # request.urlretrieve(img, './' + path + '/' + name + '.jpg') except error.URLError as e: print(e.reason)if __name__ == '__main__': page = 1 taobao = TaoBao() taobao.get_connect() while True: content = taobao.get_html(page) if content == -1: print('抓取完毕!') exit() # 解析json taobao.parser_json(content, page) page += 1
版权声明:
本站文章均来自互联网搜集,如有侵犯您的权益,请联系我们删除,谢谢。
标签: #python爬虫淘宝mm