#!/usr/bin/env python
# -*- coding:utf-8 -*-
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.selector import Selector
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.http import Request, FormRequest
from zhihu.items import ZhihuItem
class ZhihuSipder(CrawlSpider) :
name = "zhihu"
allowed_domains = ["www.zhihu.com"]
start_urls = [
"http://www.zhihu.com"
]
rules = (
Rule(SgmlLinkExtractor(allow = ('/question/\d+#.*?', )), callback = 'parse_page', follow = True),
Rule(SgmlLinkExtractor(allow = ('/question/\d+', )), callback = 'parse_page', follow = True),
)
headers = {
"Accept": "*/*",
"Accept-Encoding": "gzip,deflate",
"Accept-Language": "en-US,en;q=0.8,zh-TW;q=0.6,zh;q=0.4",
"Connection": "keep-alive",
"Content-Type":" application/x-www-form-urlencoded; charset=UTF-8",
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.111 Safari/537.36",
"Referer": "http://www.zhihu.com/"
}
#重写了爬虫类的方法, 实现了自定义请求, 运行成功后会调用callback回调函数
def start_requests(self):
return [Request("https://www.zhihu.com/login", meta = {'cookiejar' : 1}, callback = self.post_login)]
#FormRequeset出问题了
def post_login(self, response):
print 'Preparing login'
#下面这句话用于抓取请求网页后返回网页中的_xsrf字段的文字, 用于成功提交表单
xsrf = Selector(response).xpath('//input[@name="_xsrf"]/@value').extract()[0]
print xsrf
#FormRequeset.from_response是Scrapy提供的一个函数, 用于post表单
#登陆成功后, 会调用after_login回调函数
return [FormRequest.from_response(response, #"http://www.zhihu.com/login",
meta = {'cookiejar' : response.meta['cookiejar']},
headers = self.headers, #注意此处的headers
formdata = {
'_xsrf': xsrf,
'email': '1095511864@qq.com',
'password': '123456'
},
callback = self.after_login,
dont_filter = True
)]
def after_login(self, response) :
for url in self.start_urls :
yield self.make_requests_from_url(url)
def parse_page(self, response):
problem = Selector(response)
item = ZhihuItem()
item['url'] = response.url
item['name'] = problem.xpath('//span[@class="name"]/text()').extract()
print item['name']
item['title'] = problem.xpath('//h2[@class="zm-item-title zm-editable-content"]/text()').extract()
item['description'] = problem.xpath('//div[@class="zm-editable-content"]/text()').extract()
item['answer']= problem.xpath('//div[@class=" zm-editable-content clearfix"]/text()').extract()
return item
五、Item类和抓取间隔完整的知乎爬虫代码链接
from scrapy.item import Item, Field
class ZhihuItem(Item):
# define the fields for your item here like:
# name = scrapy.Field()
url = Field() #保存抓取问题的url
title = Field() #抓取问题的标题
description = Field() #抓取问题的描述
answer = Field() #抓取问题的答案
name = Field() #个人用户的名称
设置抓取间隔, 访问由于爬虫的过快抓取, 引发网站的发爬虫机制, 在setting.py中设置
BOT_NAME = 'zhihu'
SPIDER_MODULES = ['zhihu.spiders']
NEWSPIDER_MODULE = 'zhihu.spiders'
DOWNLOAD_DELAY = 0.25 #设置下载间隔为250ms
更多设置可以查看官方文档
抓取结果(只是截取了其中很少一部分)
...
'url': 'http://www.zhihu.com/question/20688855/answer/16577390'}
2014-12-19 23:24:15+0800 [zhihu] DEBUG: Crawled (200) (referer: http://www.zhihu.com/question/20688855/answer/19231794)
[]
2014-12-19 23:24:15+0800 [zhihu] DEBUG: Scraped from <200 http://www.zhihu.com/question/20688855/answer/15861368>
{'answer': [u'\u9009\u4f1a\u8ba1\u8fd9\u4e2a\u4e13\u4e1a\uff0c\u8003CPA\uff0c\u5165\u8d22\u52a1\u8fd9\u4e2a\u884c\u5f53\u3002\u8fd9\u4e00\u8def\u8d70\u4e0b\u6765\uff0c\u6211\u53ef\u4ee5\u5f88\u80af\u5b9a\u7684\u544a\u8bc9\u4f60\uff0c\u6211\u662f\u771f\u7684\u559c\u6b22\u8d22\u52a1\uff0c\u70ed\u7231\u8fd9\u4e2a\u884c\u4e1a\uff0c\u56e0\u6b64\u575a\u5b9a\u4e0d\u79fb\u5730\u5728\u8fd9\u4e2a\u884c\u4e1a\u4e2d\u8d70\u4e0b\u53bb\u3002',
u'\u4e0d\u8fc7\u4f60\u8bf4\u6709\u4eba\u4ece\u5c0f\u5c31\u559c\u6b22\u8d22\u52a1\u5417\uff1f\u6211\u89c9\u5f97\u51e0\u4e4e\u6ca1\u6709\u5427\u3002\u8d22\u52a1\u7684\u9b45\u529b\u5728\u4e8e\u4f60\u771f\u6b63\u61c2\u5f97\u5b83\u4e4b\u540e\u3002',
u'\u901a\u8fc7\u5b83\uff0c\u4f60\u53ef\u4ee5\u5b66\u4e60\u4efb\u4f55\u4e00\u79cd\u5546\u4e1a\u7684\u7ecf\u8425\u8fc7\u7a0b\uff0c\u4e86\u89e3\u5176\u7eb7\u7e41\u5916\u8868\u4e0b\u7684\u5b9e\u7269\u6d41\u3001\u73b0\u91d1\u6d41\uff0c\u751a\u81f3\u4f60\u53ef\u4ee5\u638c\u63e1\u5982\u4f55\u53bb\u7ecf\u8425\u8fd9\u79cd\u5546\u4e1a\u3002',
u'\u5982\u679c\u5bf9\u4f1a\u8ba1\u7684\u8ba4\u8bc6\u4ec5\u4ec5\u505c\u7559\u5728\u505a\u5206\u5f55\u8fd9\u4e2a\u5c42\u9762\uff0c\u5f53\u7136\u4f1a\u89c9\u5f97\u67af\u71e5\u65e0\u5473\u3002\u5f53\u4f60\u5bf9\u5b83\u7684\u8ba4\u8bc6\u8fdb\u5165\u5230\u6df1\u5c42\u6b21\u7684\u65f6\u5019\uff0c\u4f60\u81ea\u7136\u5c31\u4f1a\u559c\u6b22\u4e0a\u5b83\u4e86\u3002\n\n\n'],
'description': [u'\u672c\u4eba\u5b66\u4f1a\u8ba1\u6559\u80b2\u4e13\u4e1a\uff0c\u6df1\u611f\u5176\u67af\u71e5\u4e4f\u5473\u3002\n\u5f53\u521d\u662f\u51b2\u7740\u5e08\u8303\u4e13\u4e1a\u62a5\u7684\uff0c\u56e0\u4e3a\u68a6\u60f3\u662f\u6210\u4e3a\u4e00\u540d\u8001\u5e08\uff0c\u4f46\u662f\u611f\u89c9\u73b0\u5728\u666e\u901a\u521d\u9ad8\u4e2d\u8001\u5e08\u5df2\u7ecf\u8d8b\u4e8e\u9971\u548c\uff0c\u800c\u987a\u6bcd\u4eb2\u5927\u4eba\u7684\u610f\u9009\u4e86\u8fd9\u4e2a\u4e13\u4e1a\u3002\u6211\u559c\u6b22\u4e0a\u6559\u80b2\u5b66\u7684\u8bfe\uff0c\u5e76\u597d\u7814\u7a76\u5404\u79cd\u6559\u80b2\u5fc3\u7406\u5b66\u3002\u4f46\u4f1a\u8ba1\u8bfe\u4f3c\u4e4e\u662f\u4e3b\u6d41\u3001\u54ce\u3002\n\n\u4e00\u76f4\u4e0d\u559c\u6b22\u94b1\u4e0d\u94b1\u7684\u4e13\u4e1a\uff0c\u6240\u4ee5\u5f88\u597d\u5947\u5927\u5bb6\u9009\u4f1a\u8ba1\u4e13\u4e1a\u5230\u5e95\u662f\u51fa\u4e8e\u4ec0\u4e48\u76ee\u7684\u3002\n\n\u6bd4\u5982\u8bf4\u5b66\u4e2d\u6587\u7684\u4f1a\u8bf4\u4ece\u5c0f\u559c\u6b22\u770b\u4e66\uff0c\u4f1a\u6709\u4ece\u5c0f\u559c\u6b22\u4f1a\u8ba1\u501f\u554a\u8d37\u554a\u7684\u7684\u4eba\u5417\uff1f'],
'name': [],
'title': [u'\n\n', u'\n\n'],
'url': 'http://www.zhihu.com/question/20688855/answer/15861368'}
...
六、存在问题
Rule设计不能实现全网站抓取, 只是设置了简单的问题的抓取
Xpath设置不严谨, 需要重新思考
Unicode编码应该转换成UTF-8
本文原创发布php中文网,转载请注明出处,感谢您的尊重!
相关文章
相关视频
网友评论
文明上网理性发言,请遵守 新闻评论服务协议我要评论
立即提交
专题推荐独孤九贱-php全栈开发教程
全栈 100W+
主讲:Peter-Zhu 轻松幽默、简短易学,非常适合PHP学习入门
玉女心经-web前端开发教程
入门 50W+
主讲:灭绝师太 由浅入深、明快简洁,非常适合前端学习入门
天龙八部-实战开发教程
实战 80W+
主讲:西门大官人 思路清晰、严谨规范,适合有一定web编程基础学习