python爬虫 抓取图片入门

晚上没事的时候和室友聊聊爬虫的事，大概了解了下原理和思路，简单的都是获取页面，然后匹配目标，然后再load下来。具体大型的爬虫项目就得取得目标目录（索引）然后再通过索引去找到目标url，再去定位资源，接着清洗资源。
demo如下，抓取同性交友网站的略缩图，结果如下

python 2.7.12

# -*- coding:utf-8 -*-
from requests import Session
import re

class Bilibili():
    def __init__(self):
        self.session = self._get_new_session()
        self.host = 'http://www.b.com'

    def start_work(self):
        resp = self.session.get("http://www.b.com/")
        content = resp.content
        reg = r'src="(.+?\.jpg)" alt'
        imgre = re.compile(reg)
        imglist = re.findall(imgre, content)
        i = 100
        for img_url in imglist:
            self.download_img(img_url, str(i))
            i += 1

    def download_img(self, url, name):
        resp = self.session.get(url)
        image_conten = resp.content
        file_path = './images/{0}.jpg'.format(name)
        with open(file_path, 'wb') as fw:
            fw.write(image_conten)


    def _get_new_session(self):
        s = Session()
        return s

if __name__ == '__main__':
    test = Bilibili()
    test.start_work()