Python インスタント Web クローラー プロジェクト: コンテンツ エクストラクターの定義

#!/usr/bin/python
# -*- coding: utf-8 -*-
# 模块名: gooseeker_py2
# 类名: GsExtractor
# Version: 2.0
# 适配Python版本: 2.7
# 说明: html内容提取器
# 功能: 使用xslt作为模板，快速提取HTML DOM中的内容。
# released by 集搜客(http://www.gooseeker.com) on May 18, 2016
# github: https://github.com/FullerHua/jisou/core/gooseeker_py2.py

from urllib2 import urlopen
from urllib import quote
from lxml import etree
import time

class GsExtractor(object):
    def _init_(self):
        self.xslt = ""
    # 从文件读取xslt
    def setXsltFromFile(self , xsltFilePath):
        file = open(xsltFilePath , 'r')
        try:
            self.xslt = file.read()
        finally:
            file.close()
    # 从字符串获得xslt
    def setXsltFromMem(self , xsltStr):
        self.xslt = xsltStr
    # 通过GooSeeker API接口获得xslt
    def setXsltFromAPI(self , APIKey , theme, middle=None, bname=None):
        apiurl = "http://www.gooseeker.com/api/getextractor?key="+ APIKey +"&theme="+quote(theme)
        if (middle):
            apiurl = apiurl + "&middle="+quote(middle)
        if (bname):
            apiurl = apiurl + "&bname="+quote(bname)
        apiconn = urlopen(apiurl)
        self.xslt = apiconn.read()
    # 返回当前xslt
    def getXslt(self):
        return self.xslt
    # 提取方法，入参是一个HTML DOM对象，返回是提取结果
    def extract(self , html):
        xslt_root = etree.XML(self.xslt)
        transform = etree.XSLT(xslt_root)
        result_tree = transform(html)
        return result_tree

# _*_coding:utf8_*_
# douban_py2.py
# 爬取豆瓣小组讨论话题
# Python版本: 2.7

from lxml import etree
from gooseeker_py2 import GsExtractor
from selenium import webdriver
import time

class PhantomSpider:
    def getContent(self, url):
        browser = webdriver.PhantomJS(executable_path='C:\\phantomjs-2.1.1-windows\\bin\\phantomjs.exe')
        browser.get(url)
        time.sleep(3)
        html = browser.execute_script("return document.documentElement.outerHTML")
        output = etree.HTML(html)
        return output

    def saveContent(self, filepath, content):
        file_obj = open(filepath, 'w')
        file_obj.write(content)
        file_obj.close()

doubanExtra = GsExtractor()   
# 下面这句调用gooseeker的api来设置xslt抓取规则
# 第一个参数是app key，请到GooSeeker会员中心申请
# 第二个参数是规则名，是通过GooSeeker的图形化工具: 谋数台MS 来生成的
doubanExtra.setXsltFromAPI("ffd5273e213036d812ea298922e2627b" , "豆瓣小组讨论话题")  

url = "https://www.douban.com/group/haixiuzu/discussion?start="
totalpages = 5
doubanSpider = PhantomSpider()
print("爬取开始")

for pagenumber in range(1 , totalpages):
    currenturl = url + str((pagenumber-1)*25)
    print("正在爬取", currenturl)
    content = doubanSpider.getContent(currenturl)
    outputxml = doubanExtra.extract(content)
    outputfile = "result" + str(pagenumber) +".xml"
    doubanSpider.saveContent(outputfile , str(outputxml))

print("爬取结束")