...python の 学习

5.14

...上次学python 好像是一个月前..

写点东西记录下叭..

现在在看李老大写的博客写..可能直接开抄代码...

感觉自己写的总是爬不成功，之前写的爬豆瓣影评的爬虫还是残的...

1.最简单的爬取一个网页

import urllib2
html = urllib2.urlopen('http://music.163.com/')
print html.read()

2.把爬取到的网页存起来

可是好像因为之前用了那个网页映射工具，现在生成 的 html 里面是当前目录下的东西，而不是自己爬的那个网页里面的内容...sigh..

import urllib2
response = urllib2.urlopen('http://music.163.com/')
html = response.read()
open('testt.html',"w").write(html)

3.爬取ZOL 的一张壁纸

import urllib2
import re # 正则表达式所用到的库

# 我们所要下载的图片所在网址
url = 'http://desk.zol.com.cn/bizhi/6377_78500_2.html'
response = urllib2.urlopen(url)
# 获取网页内容
html = response.read()

# 确定一个正则表达式，用来找到图片的所在地址
reg = re.compile(r'<img id="bigImg" src="(.*?jpg)" .*>');
imgurl = reg.findall(html)[]

# 打开图片并保存为haha.jpg
imgsrc = urllib2.urlopen(imgurl).read()
open("haha.jpg","w").write(imgsrc)

是直接抄的老大的代码

然而我爬出来的壁纸是这样的

不懂啊

解决了......

http://m.ithao123.cn/content-6589593.html

应该用 "wb" 去打开文件

import urllib2
import re

url = 'http://desk.zol.com.cn/bizhi/6377_78500_2.html'
response = urllib2.urlopen(url)

html = response.read()

reg = re.compile(r'<img id="bigImg" src="(.*?jpg)" .*>');
imgurl = reg.findall(html)[]

imgsrc = urllib2.urlopen(imgurl).read()
open("haha.jpg","wb").write(imgsrc)

然后

可以看到壁纸了，感人！！！

5.15

今天试了下李老大爬ZOL 壁纸 的代码，爬出来的文件夹里面是空的啊...而且文件名是乱码..

不过李老大说了那个只适用于linux

于是开始看 崔庆才 教程

1.爬取贴吧帖子

效果图

然后在抄代码的过程中遇到三个问题

1) print 中文的时候会报错

一种解决方案是 这个

#!/usr/bin/python
 #coding:utf-

这篇博客讲的

2）然后在改了上面那个问题后

会报错，像下面这样

解决办法就是图里面说的这样

3.最后一个问题 就是 贴吧改版了

要换成

<h3 class="core_title_txt".*?>(.*?)</h3>

最后代码是这样的

#!/usr/bin/python
#coding:utf-
__author__ = 'CQC'
# -*- coding:utf- -*-

import urllib
import urllib2
import re

class Tool:

    removeImg = re.compile('<img.*?>| {7}|')

    removeAddr = re.compile('<a.*?>|</a>')

    replaceLine = re.compile('<tr>|<div>|</div>|</p>')

    replaceTD= re.compile('<td>')

    replacePara = re.compile('<p.*?>')

    replaceBR = re.compile('<br><br>|<br>')

    removeExtraTag = re.compile('<.*?>')
    def replace(self,x):
        x = re.sub(self.removeImg,"",x)
        x = re.sub(self.removeAddr,"",x)
        x = re.sub(self.replaceLine,"\n",x)
        x = re.sub(self.replaceTD,"\t",x)
        x = re.sub(self.replacePara,"\n    ",x)
        x = re.sub(self.replaceBR,"\n",x)
        x = re.sub(self.removeExtraTag,"",x)

        return x.strip()

class BDTB:

    def __init__(self,baseUrl,seeLZ,floorTag):

        self.baseURL = baseUrl

        self.seeLZ = '?see_lz='+str(seeLZ)

        self.tool = Tool()

        self.file = None

        self.floor = 

        self.defaultTitle = u"百度贴吧"

        self.floorTag = floorTag

    def getPage(self,pageNum):
        try:

            url = self.baseURL+ self.seeLZ + '&pn=' + str(pageNum)
            request = urllib2.Request(url)
            response = urllib2.urlopen(request)

            return response.read().decode('utf-8','ignore')

        except urllib2.URLError, e:
            if hasattr(e,"reason"):
                print u"连接百度贴吧失败,错误原因",e.reason
                return None

    def getTitle(self,page):

        pattern = re.compile('<h3 class=core_title_txt.*?>(.*?)</h3>',re.S)
        result = re.search(pattern,page)
        if result:

            return result.group().strip()
        else:
            return None

    def getPageNum(self,page):

        pattern = re.compile('<li class="l_reply_num.*?</span>.*?<span.*?>(.*?)</span>',re.S)
        result = re.search(pattern,page)
        if result:
            return result.group().strip()
        else:
            return None

    def getContent(self,page):

        pattern = re.compile('<div id="post_content_.*?>(.*?)</div>',re.S)
        items = re.findall(pattern,page)
        contents = []
        for item in items:

            content = "\n"+self.tool.replace(item)+"\n"
            contents.append(content.encode('utf-8'))
        return contents

    def setFileTitle(self,title):

        if title is not None:
            self.file = open(title + ".txt","w+")
        else:
            self.file = open(self.defaultTitle + ".txt","w+")

    def writeData(self,contents):

        for item in contents:
            if self.floorTag == '':

                floorLine = "\n" + str(self.floor) + u"-----------------------------------------------------------------------------------------\n"
                self.file.write(floorLine)
            self.file.write(item)
            self.floor += 

    def start(self):
        indexPage = self.getPage()
        pageNum = self.getPageNum(indexPage)
        title = self.getTitle(indexPage)
        self.setFileTitle(title)
        if pageNum == None:
            print "URL已失效，请重试"
            return
        try:
            print "该帖子共有" + str(pageNum) + "页"
            for i in range(,int(pageNum)+):
                print "正在写入第" + str(i) + "页数据"
                page = self.getPage(i)
                contents = self.getContent(page)
                self.writeData(contents)

        except IOError,e:
            print "写入异常，原因" + e.message
        finally:
            print "写入任务完成"

print u"请输入帖子代号"
baseURL = 'http://tieba.baidu.com/p/' + str(raw_input(u'http://tieba.baidu.com/p/'))
seeLZ = raw_input("是否只获取楼主发言，是输入1，否输入0\n")
floorTag = raw_input("是否写入楼层信息，是输入1，否输入0\n")
bdtb = BDTB(baseURL,seeLZ,floorTag)
bdtb.start()

还不懂原理，再看

5.18

爬取贴吧内容的 一个类

#!/usr/bin/python
#coding:utf-
import urllib
import urllib2
import re

class bdtb:
    def __init__(self,baseurl,seelz):
        self.baseurl = baseurl
        self.seelz = '?see_lz='+str(seelz)

    def getPage(self,pagenum):
        try:
            url = self.baseurl + self.seelz + '&pn=' + str(pagenum)
            request = urllib2.Request(url)
            response = urllib2.urlopen(request)
            print response.read()
            return response
        except urllib2.URLError,e:
            if hasattr(e,"reason"):
                print u"连接百度贴吧失败，错误原因",e.reason
                return None

baseurl = 'http://tieba.baidu.com/p/3138733512'
bb = bdtb(baseurl,)
bb.getPage()

5.19

模拟登陆学校的信息门户

要用 ie 才能够看到成绩，但是看不到表单，就是 form data

这个时候再用回搜狗

#coding=utf-

import urllib
import urllib2
import cookielib
import re

class CHD:

    def __init__(self):
        self.loginUrl = 'http://bksjw.chd.edu.cn/loginAction.do'
        self.cookies = cookielib.CookieJar()
        self.postdata = urllib.urlencode({
            'dllx':dldl
            'zjh':xxxx
            'mm':xxxx
        })
        self.opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(self.cookies))

    def getPage(self):
        request = urllib2.Request(
            url = self.loginUrl,
            data = self.postdata)
        result = self.opener.open(request)

        print result.read().decode('gbk')

    chd = CHD()
    chd.getPage()