Python 抓取花瓣图片地址

环境准备

1. Python 2.7
2. BeautifulSoup

BeautifulSoup 安装

教程

实现代码

import urllib2
import types
from bs4 import BeautifulSoup


def parseHtml(startPageUrl):
    req=urllib2.Request(startPageUrl)
    response=urllib2.urlopen(req)
    html=response.read()

    soup = BeautifulSoup(html)
    tags=soup.findAll('a')

    for tag in tags:
        if isinstance(tag.get('class'),list):
            if 'layer-view' in tag.get('class'):
                lastMax= tag.get('href')[6:-1]
                print "http:"+tag.find('img')['src']
    return lastMax

startPageUrl="https://huaban.com/explore/hua/?j450erym&max=0&limit=20&wfl=1"
lastMax=parseHtml(startPageUrl)
while ((not lastMax) == False):
    print lastMax
    startPageUrl='https://huaban.com/explore/hua/?j450erym&max='+lastMax+'&limit=20&wfl=1'
    lastMax=parseHtml(startPageUrl)