python爬虫获取淘宝妹子信息和相片

python爬虫练习，使用beautifulsoup +sublime text 3 + python3.6版本。

上图！！！

只抓取了少量图片

一、爬虫网址：https://mm.taobao.com/json/request_top_list.htm?page=1

使用urllib库中的request获取网页信息

	def __init__(self):
		self.siteUrl = "https://mm.taobao.com/json/request_top_list.htm"


	def getHtml(self,pageIndex):
		url = self.siteUrl+"?page="+pageIndex
		print("\nurl="+url+"\n")
		req = request.Request(url)
		response = request.urlopen(req)
		return response.read().decode('gbk')

二、提取页面中的标签信息（div，class=‘list-item’）

	def getListItems(self,pageIndex):
		'使用beautifulsoup提取div标签'
		soup = BeautifulSoup(self.getHtml(str(pageIndex)),'html.parser')
		divs = soup.find_all('div',class_='list-item')
		return divs

三、根据提取到的img标签中url地址，保存图片文件到本地

def saveFile(self,imgurl):
		'保存图片文件到目录images下'
		if imgurl == None:
			return
		if not imgurl.startswith('https:'):
			imgurl = 'https:' + imgurl
		path = 'images'
		isExist = os.path.exists(path)
		if not isExist:
			os.makedirs(path)
		req = request.Request(imgurl)
		response = request.urlopen(req)
		data = response.read()
		if data == None:
			return

		path = path + '/' + str(time.time())+".jpg"
		f = open(path,'wb')
		f.write(data)

		f.close()

四、保存提取到的个人信息简介到info.txt文件

	def savePersonalInfo(self,div):
		'保存个人信息到文件 info.txt'
		ladyNames = div.find('a',class_='lady-name')
		name = ladyNames.get_text()
		print('name='+str(name))
		data = str(name) +':'+ str(div.find('p',class_='description').get_text())+'\n'
		f = open('info.txt','a+')
		f.write(data)
		f.close

----------------------至此就完成了，简单爬虫功能-----------------------------------------------

完整代码：

#!usr/bin/python
from urllib import request
from urllib import parse
from bs4 import BeautifulSoup
import time
import os

class Spider(object):
	"""docstring for Spider"""
	def __init__(self):
		self.siteUrl = "https://mm.taobao.com/json/request_top_list.htm"


	def getHtml(self,pageIndex):
		url = self.siteUrl+"?page="+pageIndex
		print("\nurl="+url+"\n")
		req = request.Request(url)
		response = request.urlopen(req)
		return response.read().decode('gbk')

	def getListItems(self,pageIndex):
		'使用beautifulsoup提取div标签'
		soup = BeautifulSoup(self.getHtml(str(pageIndex)),'html.parser')
		divs = soup.find_all('div',class_='list-item')
		return divs

	def saveFile(self,imgurl):
		'保存图片文件到目录images下'
		if imgurl == None:
			return
		if not imgurl.startswith('https:'):
			imgurl = 'https:' + imgurl
		path = 'images'
		isExist = os.path.exists(path)
		if not isExist:
			os.makedirs(path)
		req = request.Request(imgurl)
		response = request.urlopen(req)
		data = response.read()
		if data == None:
			return

		path = path + '/' + str(time.time())+".jpg"
		f = open(path,'wb')
		f.write(data)

		f.close()

	def savePersonalInfo(self,div):
		'保存个人信息到文件 info.txt'
		ladyNames = div.find('a',class_='lady-name')
		name = ladyNames.get_text()
		print('name='+str(name))
		data = str(name) +':'+ str(div.find('p',class_='description').get_text())+'\n'
		f = open('info.txt','a+')
		f.write(data)
		f.close


	def start(self,start,ends):
		if start < 0:
			start = 1
		if ends < 0:
			ends = 1
		for i in range(start,ends+1):
			divs = self.getListItems(i)
			for div in divs:
				self.savePersonalInfo(div)
				link = div.find('img')
				imgurl = str(link.get('src'))
				if not imgurl.__contains__('spaceball'):
					print("img="+imgurl)
					self.saveFile(imgurl)

			pass


spider = Spider()
spider.start(2,3)