Python爬虫实战（4）：豆瓣小组话题数据采集---动态网页，采集失败啊，是哪里的问题呢？ - 集搜客GooSeeker网络爬虫

#!/usr/bin/python
# -*- coding: utf-8 -*-
# 模块名: gooseeker
# 类名: GsExtractor
# Version: 2.1
# 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.py
import time
from urllib import request
from urllib.parse import quote
from lxml import etree
class GsExtractor(object):
def _init_(self):
self.xslt = ""
# 从文件读取xslt
def setXsltFromFile(self , xsltFilePath):
file = open(xsltFilePath , 'r' , encoding='UTF-8')
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 = request.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
# 提取方法，入参是html源码，返回是提取结果
def extractHTML(self , html):
doc = etree.HTML(html)
return self.extract(doc)

复制代码

# _*_coding:utf-8_*_
# douban.py
# 爬取豆瓣小组讨论话题
from urllib import request
from lxml import etree
from gooseeker import GsExtractor
from selenium import webdriver
class PhantomSpider:
def getContent(self, url):
browser = webdriver.PhantomJS(executable_path='H:\\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', encoding='UTF-8')
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")

复制代码

复制代码