我的第一个爬虫

# 环境python 3.5.2 + beautifulsoup  

# 准备工作:了解 python 自带的模块 urllib + beautifulsoup 的网页解析

#爬取了一个图片网站的部分图片

from urllib import request
from bs4 import BeautifulSoup
import os
import os.path
import re

try:
	response = request.urlopen('https://www.4493.com/weimeixiezhen/')       #使用urlopen方法下载网页
	soup = BeautifulSoup(response,'html.parser', from_encoding = 'utf-8')
	print("来自源URL要爬取的所有网页")
	links = soup.find_all('a', href = re.compile(r"/weimeixiezhen/120"))
	count = 1                                                               # 记录下载的图片数目
	for link in links:
		urls = link['href']
		print(urls)
		url = 'https://www.4493.com'+urls
		print("具体网页： ", url)
		try:
			response_1 = request.urlopen(url)
			soup_1 = BeautifulSoup(response_1,'html.parser', from_encoding = 'utf-8')
			img = soup_1.find('img', onload = re.compile(r"btn"))
		except request.HTTPError as e:
			print(e.code)
		except request.URLError as e:
			print(e.reason)
		p = os.path.join('E:\\', "MV_img")
		if not os.path.exists(p):                                         # 判断当前目录是否存在
			os.mkdir(p)                                                   # 如果存在，才创建新的目录
		url = img['src']                                                  # 获取图片的资源链接url
		request.urlretrieve(url, 'E:\\MV_img\\MM_%s.jpg' %count)          # 根据图片的资源链接下载图片
		print('第%d张图片下载完成'%count)
		count += 1
except request.HTTPError as e :
	print(e.code)
except request.URLError as e :
	print(e.reason)
else:
	print("ok")