在scrapy中怎麼讓Spider自動去抓取豆瓣小組頁面
1，引入Scrapy中的另一個預定義的蜘蛛CrawlSpider
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
2， 基於CrawSpider定義一個新的類GroupSpider，並添加相應的爬行規則。
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/[^/]+/$', )), callback='parse_group_home_page', process_request='add_cookie'),
Rule(SgmlLinkExtractor(allow=('/group/explore\?tag', )), follow=True, process_request='add_cookie'),
]rules定義是CrawlSpider中最重要的一環，可以理解爲：當蜘蛛看到某種類型的網頁，如何去進行處理。
例如，如下規則會處理URL以/group/XXXX/爲後綴的網頁，調用parse_group_home_page爲處理函數，並且會在request發送前調用add_cookie來附加cookie信息。
Rule(SgmlLinkExtractor(allow=('/group/[^/]+/$', )), callback='parse_group_home_page', process_request='add_cookie'),又如，如下規則會抓取網頁內容，並自動抓取網頁中鏈接供下一步抓取，但不會處理網頁的其他內容。
Rule(SgmlLinkExtractor(allow=('/group/explore\?tag', )), follow=True, process_request='add_cookie'),如何添加Cookie
定義如下函數，並如前面所講在Rule定義裏添加process_request=add_cookie。
def add_cookie(self, request):
request.replace(cookies=[
{'name': 'COOKIE_NAME','value': 'VALUE','domain': '.douban.com','path': '/'},
]);
return request;如何防止蜘蛛被網站Ban掉
首先可以嘗試添加登陸用戶的cookie去抓取網頁，即使你抓取的是公開網頁，添加cookie有可能會防止蜘蛛在應用程序層被禁。這個我沒有實際驗證過，但肯定沒有壞處。
其次，即使你是授權用戶，如果你的訪問過於頻繁，你的IP會可能被ban，所以一般你需要讓蜘蛛在訪問網址中間休息1~2秒。
還有就是配置User Agent，儘量輪換使用不同的UserAgent去抓取網頁
在Scrapy項目的settings.py鍾，添加如下設置：
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，抓取豆瓣小組頁面的蜘蛛就完成了。接下來，可以按照這種模式定義抓取小組討論頁面數據的Spider，然後就放手讓蜘蛛去爬行吧！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<span><span style="line-height:20px;"> </span></span>