python 爬取 明星相关图片

爬取地址：

综艺巴士 明星艺人

上源码：

#!/usr/bin/env python
#coding=utf-8
import requests
import os
import re
from bs4 import BeautifulSoup

import argparse
import hashlib
import base64
import gzip
import time
import io
class YirenSpider(object):
	headers     = {"user-agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36"}
	yiren_str   = 'http://www.zybus.com/yiren/'
	html_suffix = '.html'
	def get_html_data(self,url):
		text=requests.get(url,headers= self.headers)
		return text.content
	def get_soup(self,text):
		soup = BeautifulSoup(text, 'lxml')
		return soup
	def get_yiren_htmls(self,url):
		text    = self.get_html_data(url)
		soup    = self.get_soup(text)
		totals  = soup.find_all('a')
		img_url_list=[]
		for link in totals:
			a_link = link.get('href')
			if len(a_link) >= (len(self.yiren_str)+len(self.html_suffix)) and a_link.startswith(self.yiren_str):
				if len(img_url_list)== 0:
					img_url_list.append(a_link)
				else:
					if img_url_list.count(a_link) > 0:
						pass
					else:
						img_url_list.append(a_link)
		return img_url_list
	def get_timestr(self):
		time_now = int(time.time())
		time_local = time.localtime(time_now)
		dt = time.strftime("%Y-%m-%d_%H:%M:%S",time_local)
		return dt
	def get_img_url(self,url):#得到 图片的 html 地址
		img_prefix = 'src'
		img_suffix ='.jpg'

		text    = self.get_html_data(url)
		soup    = self.get_soup(text)
		totals  = soup.find_all('div',class_='yiren_big_pic')
		img_urls = []
		for link in totals:
			img_src = str(link)
			img_src_len = len(img_src)
			index   = img_src.find(img_prefix)
			index_r = img_src.find(img_suffix)
			img_urls.append(img_src[index+5:index_r+4])
			#print(img_src[index+5:index_r+4])
		return img_urls

	def download_images(self,urls,dirpath):#保存到指定的 文件夹
		if not os.path.exists(dirpath):
			os.makedirs(dirpath)
		for u in urls:
			u_img_data = self.get_html_data(u)
			suffix = 'jpg'
			#suffix = suffix[len(suffix) - 1]
			time.sleep(1)
			filename = str(self.get_timestr())
			with open(dirpath +'/' + filename + '.' + suffix, 'wb') as f:
				f.write(u_img_data)

	def spider(self,url,dirpath):
		htmllist = self.get_yiren_htmls(url)#得到主页 艺人的html 地址
		for html in htmllist:
			urls =self.get_img_url(html) #在某艺人的 主页上获取他那张最大的pic 图像
			self.download_images(urls,dirpath) #保存下来
			pass


if __name__ == '__main__':
	url = 'http://www.zybus.com/dlyr/'
	dir ='/home/menethis/work/Test/pythonTest/YiRen/dlyr'

	Yiren    = YirenSpider()
	Yiren.spider(url,dir)