1.手机壁纸爬取

import grequests,json,time,requests,os import uuid,re from bs4 import BeautifulSoup def imgload(url): print(len(url)) response_list = grequests.map((grequests.get(img_url) for img_url in url),size=int(len(url))) print("开始下载") for i in response_list: print(len(response_list)) filename = os.path.join('G:\手机壁纸', str(uuid.uuid4())+'.jpg') # os.path.join(os.path.abspath('.'),) with open(filename, 'wb') as f: f.write(i.content) def is_chinese(string): """ 检查整个字符串是否包含中文 :param string: 需要检查的字符串 :return: bool """ for ch in string: if u'\u4e00' <= ch <= u'\u9fff': return True return False request_list = [ grequests.get('http://m.bcoderss.com/tag/%E7%BE%8E%E5%A5%B3/page/0/'), grequests.get('http://m.bcoderss.com/tag/%E7%BE%8E%E5%A5%B3/page/1/'), grequests.get('http://m.bcoderss.com/tag/%E7%BE%8E%E5%A5%B3/page/2/'), grequests.get('http://m.bcoderss.com/tag/%E7%BE%8E%E5%A5%B3/page/3/'), grequests.get('http://m.bcoderss.com/tag/%E7%BE%8E%E5%A5%B3/page/4/') ] img_url=[] # ##### 执行并获取响应列表 ##### start_time=time.time() response_list = grequests.map(request_list,size=5) print(response_list) for i in response_list: suop = BeautifulSoup(i.text, features='html.parser') ul=suop.find('ul',id='main') li_list=ul.find_all('li') for j in li_list: img=j.find('img').attrs.get('src') if not is_chinese(img): uul=img.replace('-260x534','') print(img,uul) img_url.append(uul) print(img_url) imgload(img_url) consum=time.time()-start_time print(str(float('%.2f' % consum))+'s')