第一次写，python爬虫图片，操作excel。

 1 import urllib
 2 import urllib.request
 3 from bs4 import BeautifulSoup
 4 url = ‘http://www.dbmeinv.com/?pager_offset=1‘
 5 x=0
 6 #获取源码
 7 #自定义函数
 8 #User-Agent模拟浏览器进行访问，反爬虫
 9 def crawl(url):
10     headers={‘User-Agent‘:‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3088.3 Safari/537.36‘}
11     req=urllib.request.Request(url,headers=headers)#创建对象
12     page=urllib.request.urlopen(req,timeout=20)#设置超时
13     contents=page.read()#获取源码
14     #print (contents.decode())
15     soup = BeautifulSoup(contents,‘html.parser‘)#html.parser主要是解析网页的一种形式。
16     my_girl=soup.find_all(‘img‘)#找到所有img标签
17     # 5.获取图片
18     for girl in my_girl:#遍历
19         link=girl.get(‘src‘)#获取src
20         print(link)
21         global x#全局变量
22         # 6.下载 urlretrieve
23         urllib.request.urlretrieve(link,‘image\%s.jpg‘%x)#下载,urlretrieve(需要下载的，路径)
24         x+=1
25         print(‘正在下载第%s张‘%x)
26 #7.多页
27 for page in range(1,10):#range本身自动生成整数序列，爬取多页图片。
28     #page+=1
29     url=‘http://www.dbmeinv.com/?pager_offset={}‘.format(page)#
30     #url = ‘http://www.dbmeinv.com/?pager_offset=%d‘ % page
31     crawl(url)
32 
33 print(‘图片下载完毕‘)

import requests
from bs4 import BeautifulSoup
import xlwt
def get_content(url,headers=None,proxy=None):
    html=requests.get(url,headers=headers).content
    return html

def get_url(html):
    soup = BeautifulSoup(html,‘html.parser‘)
    shop_url_list=soup.find_all(‘div‘,class_=‘tit‘)#class在Python是关键字，
    # 列表推导式
    return [i.find(‘a‘)[‘href‘] for i in shop_url_list]

#商品的详细信息，名字，评论，人均
def get_detail_content(html):
    soup=BeautifulSoup(html,‘html.parser‘)
    price=soup.find(‘span‘,id=‘avgPriceTitle‘).text
    evaluation=soup.find(‘span‘,id=‘comment_score‘).find_all(‘span‘,class_=‘item‘)#find_all是有多个，这里三个
    #for i in evaluation:
     #   print(i.text)
    the_star=soup.find(‘div‘,class_=‘brief-info‘).find(‘span‘)[‘title‘]
    title=soup.find(‘div‘,class_=‘breadcrumb‘).find(‘span‘).text
    comments=soup.find(‘span‘,id=‘reviewCount‘).text
    address=soup.find(‘span‘,itemprop=‘street-address‘).text
    print(u‘店名：‘+title)
    for i in evaluation:
        print(i.text)
    print(price)
    print(u‘评论数量：‘+comments)
    print(u‘地址：‘+address.strip())
    print(u‘评价星级：‘+the_star)
    print(‘================‘)
    return (title,evaluation[0].text,evaluation[1].text,evaluation[2].text,price,comments,address,the_star)

if __name__==‘__main__‘:
    items=[]
    start_url=‘https://www.dianping.com/search/category/344/10/‘
    base_url=‘https://www.dianping.com‘
    headers={
        ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3088.3 Safari/537.36‘,
        ‘Cookie‘:‘_hc.v=461407bd-5a08-f3fa-742e-681a434748bf.1496365678; __utma=1.1522471392.1496365678.1496365678.1496365678.1; __utmc=1; __utmz=1.1496365678.1.1.utmcsr=baidu|utmccn=(organic)|utmcmd=organic; PHOENIX_ID=0a0102b7-15c6659b548-25fc89; s_ViewType=10; JSESSIONID=E815A43E028078AFA73AF08D9C9E4A15; aburl=1; cy=344; cye=changsha; __mta=147134984.1496365814252.1496383356849.1496383925586.4‘
    }

    start_html=get_content(start_url)
    #一页
    # url_list=get_url(start_html)
    #多页
    url_list = [base_url + url for url in get_url(start_html)]
    for i in url_list:
        detail_html=get_content(i,headers=headers)
        item=get_detail_content(detail_html)
        items.append(item)

    #写excel，txt差别，Excel：xlwg
    newTable=‘DZDP.xls‘
    wb=xlwt.Workbook(encoding=‘utf-8‘)
    ws=wb.add_sheet(‘test1‘)
    headData=[‘商户名字‘,‘口味评分‘,‘环境评分‘,‘服务评分‘,‘人均价格‘,‘评论数量‘,‘地址‘,‘商户评价‘]
    for colnum in range(0,8):
        ws.write(0,colnum,headData[colnum],xlwt.easyxf(‘font:bold on‘))
    index=1
    lens=len(items)
    for j in range(0,lens):
        for i in range(0,8):
            ws.write(index,i,items[j][i])
        index +=1
    wb.save(newTable)