用Scrapy抓取豆瓣小组数据（二）

接着上篇博客《用Scrapy抓取豆瓣小组数据（一)》http://my.oschina.net/chengye/blog/124157

在scrapy中怎么让Spider自动去抓取豆瓣小组页面

1，引入Scrapy中的另外一个预约义的蜘蛛CrawlSpider

from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor

2， 基于CrawSpider定义一个新的类GroupSpider，并添加相应的爬行规则。

class GroupSpider(CrawlSpider):
	name = "Group"
	allowed_domains = ["douban.com"]
	start_urls = [
		"http://www.douban.com/group/explore?tag=%E8%B4%AD%E7%89%A9",
		"http://www.douban.com/group/explore?tag=%E7%94%9F%E6%B4%BB",
		"http://www.douban.com/group/explore?tag=%E7%A4%BE%E4%BC%9A",
		"http://www.douban.com/group/explore?tag=%E8%89%BA%E6%9C%AF",
		"http://www.douban.com/group/explore?tag=%E5%AD%A6%E6%9C%AF",
		"http://www.douban.com/group/explore?tag=%E6%83%85%E6%84%9F",
		"http://www.douban.com/group/explore?tag=%E9%97%B2%E8%81%8A",
		"http://www.douban.com/group/explore?tag=%E5%85%B4%E8%B6%A3"
	]

	rules = [
		Rule(SgmlLinkExtractor(allow=('/group/[^/]+/$', )), callback='parse_group_home_page', process_request='add_cookie'),
		Rule(SgmlLinkExtractor(allow=('/group/explore\?tag', )), follow=True, process_request='add_cookie'),
	]

start_urls预约义了豆瓣有所小组分类页面，蜘蛛会从这些页面出发去找小组。

rules定义是CrawlSpider中最重要的一环，能够理解为：当蜘蛛看到某种类型的网页，如何去进行处理。

例如，以下规则会处理URL以/group/XXXX/为后缀的网页，调用parse_group_home_page为处理函数，而且会在request发送前调用add_cookie来附加cookie信息。

Rule(SgmlLinkExtractor(allow=('/group/[^/]+/$', )), callback='parse_group_home_page', process_request='add_cookie'),

又如，以下规则会抓取网页内容，并自动抓取网页中连接供下一步抓取，但不会处理网页的其余内容。

Rule(SgmlLinkExtractor(allow=('/group/explore\?tag', )), follow=True, process_request='add_cookie'),

如何添加Cookie

定义以下函数，并如前面所讲在Rule定义里添加process_request=add_cookie。

def add_cookie(self, request):
	request.replace(cookies=[
		{'name': 'COOKIE_NAME','value': 'VALUE','domain': '.douban.com','path': '/'},
		]);
	return request;

通常网站在client端都用cookie来保存用户的session信息，添加cookie信息就能够模拟登录用户来抓取数据。

如何防止蜘蛛被网站Ban掉

首先能够尝试添加登录用户的cookie去抓取网页，即便你抓取的是公开网页，添加cookie有可能会防止蜘蛛在应用程序层被禁。这个我没有实际验证过，但确定没有坏处。

其次，即便你是受权用户，若是你的访问过于频繁，你的IP会可能被ban，因此通常你须要让蜘蛛在访问网址中间休息1~2秒。

还有就是配置User Agent，尽可能轮换使用不一样的UserAgent去抓取网页

在Scrapy项目的settings.py钟，添加以下设置：

DOWNLOAD_DELAY = 2
RANDOMIZE_DOWNLOAD_DELAY = True
USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_3) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.54 Safari/536.5'
COOKIES_ENABLED = True

================

到此位置，抓取豆瓣小组页面的蜘蛛就完成了。接下来，能够按照这种模式定义抓取小组讨论页面数据的Spider，而后就放手让蜘蛛去爬行吧！Have Fun！

from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.selector import HtmlXPathSelector
from scrapy.item import Item
from douban.items import DoubanItem
import re

class GroupSpider(CrawlSpider):
	name = "Group"
	allowed_domains = ["douban.com"]
	start_urls = [
		"http://www.douban.com/group/explore?tag=%E8%B4%AD%E7%89%A9",
		"http://www.douban.com/group/explore?tag=%E7%94%9F%E6%B4%BB",
		"http://www.douban.com/group/explore?tag=%E7%A4%BE%E4%BC%9A",
		"http://www.douban.com/group/explore?tag=%E8%89%BA%E6%9C%AF",
		"http://www.douban.com/group/explore?tag=%E5%AD%A6%E6%9C%AF",
		"http://www.douban.com/group/explore?tag=%E6%83%85%E6%84%9F",
		"http://www.douban.com/group/explore?tag=%E9%97%B2%E8%81%8A",
		"http://www.douban.com/group/explore?tag=%E5%85%B4%E8%B6%A3"
	]

	rules = [
		Rule(SgmlLinkExtractor(allow=('/group/[^/]+/$', )), callback='parse_group_home_page', process_request='add_cookie'),
	#	Rule(SgmlLinkExtractor(allow=('/group/[^/]+/discussion\?start\=(\d{1,4})$', )), callback='parse_group_topic_list', process_request='add_cookie'),
		Rule(SgmlLinkExtractor(allow=('/group/explore\?tag', )), follow=True, process_request='add_cookie'),
	]

	def __get_id_from_group_url(self, url):
		m =  re.search("^http://www.douban.com/group/([^/]+)/$", url)
		if(m):
			return m.group(1) 
		else:
			return 0



	def add_cookie(self, request):
		request.replace(cookies=[

		]);
		return request;

	def parse_group_topic_list(self, response):
		self.log("Fetch group topic list page: %s" % response.url)
		pass


	def parse_group_home_page(self, response):

		self.log("Fetch group home page: %s" % response.url)

		hxs = HtmlXPathSelector(response)
		item = DoubanItem()

		#get group name
		item['groupName'] = hxs.select('//h1/text()').re("^\s+(.*)\s+$")[0]

		#get group id 
		item['groupURL'] = response.url
		groupid = self.__get_id_from_group_url(response.url)

		#get group members number
		members_url = "http://www.douban.com/group/%s/members" % groupid
		members_text = hxs.select('//a[contains(@href, "%s")]/text()' % members_url).re("\((\d+)\)")
		item['totalNumber'] = members_text[0]

		#get relative groups
		item['RelativeGroups'] = []
		groups = hxs.select('//div[contains(@class, "group-list-item")]')
		for group in groups:
			url = group.select('div[contains(@class, "title")]/a/@href').extract()[0]
			item['RelativeGroups'].append(url)
		#item['RelativeGroups'] = ','.join(relative_groups)
		return item