利用python进行爬虫操作记录——part1百度贴吧

在进行自然语言的深入学习中，很重要的一个过程是从互联网平台上抓取文本和资料。我开始尝试进行网络爬虫。
从最简单的不需要模拟登陆的百度贴吧和豆瓣等开始。

firefox浏览器

相较于chrome浏览器而言，最近发现firefox特别好用，根本不需要什么额外的抓包，就可以实时监测而且可读性很强。
F12调取网络检测器
查看器——查看整个网页的HTML脚本，支持搜索
控制台——get/post请求的参数/响应/cookie
各项参数和记录特别具体

百度贴吧爬虫

# coding=utf-8
# -*- coding = utf-8 -*-
import urllib2
import re


class Tool:
    removeImg = re.compile(r'')  # image
    removeAddr = re.compile(r'|')
    replaceLine = re.compile('|
|
|
')
    replaceBR = re.compile('

|
')
    replaceTD = re.compile('')
    replacePara = re.compile('')
    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 BaiduTieba:
    def __init__(self, url, seelz, floortag=1):
        self.url = url
        self.seeLz = '?see_lz='+str(seelz)
        self.tool = Tool()
        self.file = None
        self.defaultTitle = "百度贴吧"
        self.floortag = floortag    # 判断是否添加楼层标志
        self.floor = 1

    def getPageContent(self, pagenum):
        url = self.url + self.seeLz + '&pn=' + str(pagenum)
        user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:53.0) Gecko/20100101 Firefox/53.0'
        headers = {'User-Agent': user_agent}
        try:
            request = urllib2.Request(url, headers=headers)
            response = urllib2.urlopen(request)
            content = response.read().decode('utf-8')
            return content
        except urllib2.URLError, e:
            if hasattr(e, 'reason'):   # 检查是否有name的属性
                print e.reason

    def get_title(self, pagenum=1):
        content = self.getPageContent(pagenum)
        pattern_title = re.compile(r'
if title:
            return title.group(1).strip()
        else:
            print None

    def get_author(self, pagenum=1):
        content = self.getPageContent(pagenum)
        pattern_author = re.compile(r'
')
        author = re.search(pattern_author, content)
        if author:
            return author.group(1).strip()
        else:
            return None

    def get_reply_page(self, pagenum=1):
        content = self.getPageContent(pagenum)
        pattern_page = re.compile(
            r'
(.*?).*?(.*?)')
        totalpage = re.search(pattern_page, content)
        if totalpage:
            return totalpage.group(1).strip(), totalpage.group(2).strip()
        else:
            return None

    def getContent(self, pagenum):
        content = self.getPageContent(pagenum)
        pattern_content = re.compile(r'
1
        contents = []
        for item in items:
            str_floor = str(floor) + u'楼——————————\n'
            tempContent = '\n'+ self.tool.replace(item)+'\n'
            contents.append(str_floor)
            contents.append(tempContent.encode('utf-8'))
            floor += 1
        return contents

    def writedata2File(self, contents):
        for item in contents:
            print u"正在写入"+ str(self.floor) + u"楼的内容"
            self.file.write(item)
            self.floor += 1

    def newFile(self, title):
        if title:
            self.file = open(title + '.txt', 'w+')
        else:
            self.file = open(self.defaultTitle + '.txt', 'w+')

    def start_spider(self, pagenum=1):   # 先获得第一页基础信息
        content = self.getPageContent(pagenum)
        title = self.get_title(pagenum)
        author = self.get_author(pagenum)
        self.newFile(title)
        totalpage = self.get_reply_page(pagenum)
        totalcontent = []
        for i in range(1, totalpage[1]+1):
            tempcontent = self.getContent(i)
            totalcontent += tempcontent
        try:
            self.writedata2File(totalcontent)
        except IOError, e:
            print '写入文件发生异常' + e.message
        finally:
            print '写入文件完成'

# 测试记录

tips: 1. re.research().group(0,1,2,3……)
2.user_agent等信息根据firefox的get请求中的响应参数决定