爬虫实战代码

最新推荐文章于 2023-01-31 08:00:00 发布

THMAIL

最新推荐文章于 2023-01-31 08:00:00 发布

阅读量863

点赞数 1

CC 4.0 BY-SA版权

分类专栏： Python

本文链接：https://blog.youkuaiyun.com/THMAIL/article/details/61617607

Python 专栏收录该内容

73 篇文章

订阅专栏

这是我的第一个爬虫作品，也算是处女作了吧这个项目主要是爬取ASP300这个网站的白金源码信息（白金源码地址：http://www.asp300.com/SoftList/27/27_1.html）。

主要内容包括get请求，伪造headers，cookie处理，正则表达式和BeautifulSoup提取信息，重构urllib2的重定向处理，保存图片到本地，用PIL去除图片水印，以及如何使用cookie去获取源码的真实下载地址(本来是写爬虫的，结果无意中发现这个网站可以用cookie和get进行重定向，重定向后的地址即真实下载地址，这个BUG我已经和站长说过了，打坏心思的人可以省省心了)

下面贴代码，关键地方已经添加注释，有不懂的地方可以在我的博客下方留言。

#coding=gb2312
import urllib2
import urllib
import cookielib
import re
from PIL import Image
from bs4 import BeautifulSoup
import socket

class MyError(Exception):
    #定义一个错误，留引发
    pass

class IgnoError(Exception):
    #定义一个错误，留引发
    pass

class RedirctHandler(urllib2.HTTPRedirectHandler):
    #重构302,301页面处理类
  """docstring for RedirctHandler"""
  def http_error_301(self, req, fp, code, msg, headers):
      if 'location' in headers:
          newurl = headers.getheaders('location')[0]
      elif 'uri' in headers:
          newurl = headers.getheaders('uri')[0]
      else:
          return
      return newurl
  def http_error_302(self, req, fp, code, msg, headers):
      if 'location' in headers:
          newurl = headers.getheaders('location')[0]
      elif 'uri' in headers:
          newurl = headers.getheaders('uri')[0]
      else:
          return
      return newurl

def Download(url,headers,num_retries=9):
    #下载url所指向的页面
    req = urllib2.Request(url, headers=headers)
    try:
        response = urllib2.urlopen(req,timeout=60)
        the_page = response.read()
        response.close()
    except urllib2.URLError,e:
        if num_retries > 0 and hasattr(e,'code') and (500 <= e.code <600):
            return Download(url,headers,num_retries - 1)
        elif hasattr(e, 'code') and (e.code == 404):
            raise IgnoError
        else:
            print 'Download Error:', e.reason
            raise MyError
    except socket.timeout:
        if num_retries > 0 :
            return Download(url, headers, num_retries - 1)
        raise socket.timeout
    return the_page

def resolve(html):
    #提取源码信息
    image_url = []
    soup = BeautifulSoup(html,"lxml")
    title = unicode(soup.head.title.string)
    title = re.search('(.*?)_ASP300',title).groups()[0]
    size = soup.find('div',class_='box').find('div',class_='box_1').find('div',id='goodsInfo').find('div',class_='textInfo').ul.find_all('li')[2].dd
    size = unicode(size)
    size = float(re.search(u'软件大小：(.*?)\D',size).groups()[0])
    summary_tag = soup.find('div',class_='s')
    summary_content = unicode(summary_tag).strip()
    summary_content = summary_content.split('<br/>')
    summary_content[0] = summary_content[0][15:]
    del summary_content[len(summary_content)-1]
    for a,b in enumerate(summary_content):
        if b == '\n':
            del summary_content[a]
    summary_cahe = u''
    for c in summary_content:
        summary_cahe += (c + u'<br/>')
    summary_content = summary_cahe
    for i in summary_tag.p.find_all('img'):
        image_url.append('http://www.asp300.com' + i['src'])
    #获取图片下载地址，放入image_url中,image_url中的元素为str，非unicode
    return title,size,summary_content,image_url#title,summary是unicode，size是float，image_url中的元素均为str

def download_image(name,url,headers,num_tries=9):
    #下载图片
    req = urllib2.Request(url=url,headers=headers)
    try:
        f = urllib2.urlopen(req,timeout=60)
    except urllib2.URLError, e:
        if num_tries > 0 and hasattr(e,'code') and 500 <= e.code <600:
            return download_image(name,url,headers,num_tries - 1)
        else:
            print '下载图片出错：',e.reason
            raise MyError
    except socket.timeout:
        if num_tries > 0 :
            return download_image(name,url,headers,num_tries - 1)
        raise socket.timeout
    image = open(name,'wb')
    image.write(f.read())
    f.close()
    image.close()

def screenshot(name,change,format):
    # 去除水印
    im = Image.open(name)
    w,h = im.size
    box = (0,0,w,h-change)
    region = im.crop(box)
    region.save(name,format)

def soft_url(url,headers,num_retries=9):
    #获取软件真实下载地址
    id = int(re.search('SoftView_(.*?).html',url).groups()[0])
    url1 = 'http://www.asp300.com/2012dll/Down.jsp?CodeID=%d&id=1'%id
    #这一步是为了获取商品的ookie
    cookie = cookielib.CookieJar()
    handler = urllib2.HTTPCookieProcessor(cookie)
    opener1 = urllib2.build_opener(handler)
    req1 = urllib2.Request(url=url1,headers=headers)
    try:
        opener1.open(req1,timeout=60)
        print '%s：获取下载COOKIE成功'%time.ctime()
    except urllib2.URLError, e:
        if num_retries > 0 and hasattr(e,'code') and (500 <= e.code <600):
            return soft_url(url,headers,num_retries - 1)
        else:
            print 'SOFT_URL1 Error:', e.reason
            raise MyError
    except socket.timeout:
        if num_retries > 0:
            return soft_url(url, headers, num_retries - 1)
        raise socket.timeout
    #cookie获取完毕
    #这一步是基于上一步的cookie，获取真是下载地址
    #debug_handler = urllib2.HTTPHandler(debuglevel=1)
    opener2 = urllib2.build_opener(RedirctHandler,handler)
    url2 = 'http://www.asp300.com/2012dll/DownBJ.jsp?CodeID=%d'%id
    req2 = urllib2.Request(url=url2,headers=headers)
    try:
        html = opener2.open(req2,timeout=60)
        print '%s：获取下载地址成功'%time.ctime()
    except urllib2.URLError, e:
        if num_retries > 0 and hasattr(e,'code') and (500 <= e.code <600):
            return soft_url(url,headers,num_retries - 1)
        else:
            print 'SOFT_URL2 Error:', e.reason
            raise MyError
    except socket.timeout:
        if num_retries > 0:
            return soft_url(url, headers, num_retries - 1)
        raise socket.timeout
    return html


if __name__ == '__main__':
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 '}
    url = 'http://www.asp300.com/SoftView/27/SoftView_61577.html'
    html = Download(url, headers)
    print '页面下载完成'
    title, size, summary_content, image_url = resolve(html)
    print '信息提取完成'
    id = 0
    for i in image_url:
        name = './image/image_cache%d.jpg' % id
        download_image(name, i, headers)
        print '图片下载完成%d' % id
        screenshot(name, 52, 'jpeg')
        print '图片转换完成'
        id += 1
    download_url = soft_url(url, headers)
    print title
    print size
    summary_content = summary_content.replace(u'\u200b',u'')#unicode特殊字符'\u200b'，不能转为gb2312
    print summary_content,type(summary_content)
    print summary_content.encode('gb2312')
    print image_url
    print download_url