环境:windows7+Python3.4
import urllib, re, sys, os,requests
path=r"D:\360Downloads\beautify\MM"
url = 'http://huaban.com/favorite/beauty'
i_headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.71 Safari/537.36"}
count=0
def urlHandle(url):req = urllib.request.Request(url, headers=i_headers)html = urllib.request.urlopen(req).read()reg = re.compile(r'"pin_id":(\d+),.+?"file":{"farm":"farm1", "bucket":"hbimg",.+?"key":"(.*?)",.+?"type":"image/(.*?)"', re.S)groups = re.findall(reg, html.decode('utf-8'))return groupsdef imgHandle(groups):if groups:for att in groups: pin_id = att[0]att_url = att[1] + '_fw236'img_type = att[2]img_url = 'http://img.hb.aicdn.com/' + att_urlr = requests.get(img_url)with open(path + att_url + '.' + img_type, 'wb') as fd:#with open(path + str(i) + '.' + img_type, 'wb') as fd:for chunk in r.iter_content():fd.write(chunk)print(att) groups = urlHandle(url)
imgHandle(groups)while(groups):count+=1print(count)pin_id = groups[-1][0]print(pin_id)urltemp = url+'/?max=' + str(pin_id) + '&limit=' + str(20) + '&wfl=1'print(urltemp)groups = urlHandle(urltemp)#print groupsimgHandle(groups)