在Scrapy基礎(chǔ)——Spider中,我簡(jiǎn)要地說了一下Spider類。Spider基本上能做很多事情了,但是如果你想爬取知乎或者是簡(jiǎn)書全站的話,你可能需要一個(gè)更強(qiáng)大的武器。
CrawlSpider基于Spider,但是可以說是為全站爬取而生。
CrawlSpider是爬取那些具有一定規(guī)則網(wǎng)站的常用的爬蟲,它基于Spider并有一些獨(dú)特屬性
· rules: 是Rule對(duì)象的集合,用于匹配目標(biāo)網(wǎng)站并排除干擾
· parse_start_url: 用于爬取起始響應(yīng),必須要返回Item,Request中的一個(gè)。
因?yàn)?i>rules是Rule對(duì)象的集合,所以這里也要介紹一下Rule。它有幾個(gè)參數(shù):link_extractor、callback=None、cb_kwargs=None、follow=None、process_links=None、process_request=None
其中的link_extractor既可以自己定義,也可以使用已有LinkExtractor類,主要參數(shù)為:
· allow:滿足括號(hào)中“正則表達(dá)式”的值會(huì)被提取,如果為空,則全部匹配。
· deny:與這個(gè)正則表達(dá)式(或正則表達(dá)式列表)不匹配的URL一定不提取。
· allow_domains:會(huì)被提取的鏈接的domains。
· deny_domains:一定不會(huì)被提取鏈接的domains。
· restrict_xpaths:使用xpath表達(dá)式,和allow共同作用過濾鏈接。還有一個(gè)類似的restrict_css
下面是官方提供的例子,我將從源代碼的角度開始解讀一些常見問題:
import scrapyfrom scrapy.spiders import CrawlSpider, Rulefrom scrapy.linkextractors import LinkExtractor
class MySpider(CrawlSpider):
name = 'example.com'
allowed_domains = ['example.com']
start_urls = ['http://www.example.com']
rules = (
# Extract links matching 'category.php' (but not matching 'subsection.php')
# and follow links from them (since no callback means follow=True by default).
Rule(LinkExtractor(allow=('category\.php', ), deny=('subsection\.php', ))),
# Extract links matching 'item.php' and parse them with the spider's method parse_item
Rule(LinkExtractor(allow=('item\.php', )), callback='parse_item'),
)
def parse_item(self, response):
self.logger.info('Hi, this is an item page! %s', response.url)
item = scrapy.Item()
item['id'] = response.xpath('//td[@id="item_id"]/text()').re(r'ID: (\d+)')
item['name'] = response.xpath('//td[@id="item_name"]/text()').extract()
item['description'] = response.xpath('//td[@id="item_description"]/text()').extract()
return item
因?yàn)?span>CrawlSpider繼承了Spider,所以具有Spider的所有函數(shù)。
首先由start_requests對(duì)start_urls中的每一個(gè)url發(fā)起請(qǐng)求(make_requests_from_url),這個(gè)請(qǐng)求會(huì)被parse接收。在Spider里面的parse需要我們定義,但CrawlSpider定義parse去解析響應(yīng)(self._parse_response(response, self.parse_start_url, cb_kwargs={}, follow=True))
_parse_response根據(jù)有無callback,follow和self.follow_links執(zhí)行不同的操作
def _parse_response(self, response, callback, cb_kwargs, follow=True):
##如果傳入了callback,使用這個(gè)callback解析頁面并獲取解析得到的reques或item
if callback:
cb_res = callback(response, **cb_kwargs) or ()
cb_res = self.process_results(response, cb_res)
for requests_or_item in iterate_spider_output(cb_res):
yield requests_or_item
## 其次判斷有無follow,用_requests_to_follow解析響應(yīng)是否有符合要求的link。
if follow and self._follow_links:
for request_or_item in self._requests_to_follow(response):
yield request_or_item
其中_requests_to_follow又會(huì)獲取link_extractor(這個(gè)是我們傳入的LinkExtractor)解析頁面得到的link(link_extractor.extract_links(response)),對(duì)url進(jìn)行加工(process_links,需要自定義),對(duì)符合的link發(fā)起Request。使用.process_request(需要自定義)處理響應(yīng)。
CrawlSpider類會(huì)在__init__方法中調(diào)用_compile_rules方法,然后在其中淺拷貝rules中的各個(gè)Rule獲取要用于回調(diào)(callback),要進(jìn)行處理的鏈接(process_links)和要進(jìn)行的處理請(qǐng)求(process_request)
def _compile_rules(self):
def get_method(method):
if callable(method):
return method
elif isinstance(method, six.string_types):
return getattr(self, method, None)
self._rules = [copy.copy(r) for r in self.rules]
for rule in self._rules:
rule.callback = get_method(rule.callback)
rule.process_links = get_method(rule.process_links)
rule.process_request = get_method(rule.process_request)
那么Rule是怎么樣定義的呢?
class Rule(object):
def __init__(self, link_extractor, callback=None, cb_kwargs=None, follow=None, process_links=None, process_request=identity):
self.link_extractor = link_extractor
self.callback = callback
self.cb_kwargs = cb_kwargs or {}
self.process_links = process_links
self.process_request = process_request
if follow is None:
self.follow = False if callback else True
else:
self.follow = follow
因此LinkExtractor會(huì)傳給link_extractor。
由上面的講解可以發(fā)現(xiàn)_parse_response會(huì)處理有callback的(響應(yīng))respons。
cb_res = callback(response, **cb_kwargs) or ()
而_requests_to_follow會(huì)將self._response_downloaded傳給callback用于對(duì)頁面中匹配的url發(fā)起請(qǐng)求(request)。
r = Request(url=link.url, callback=self._response_downloaded)
因?yàn)?span>CrawlSpider和Spider一樣,都要使用start_requests發(fā)起請(qǐng)求,用從Andrew_liu大神借鑒的代碼說明如何模擬登陸:
##替換原來的start_requests,callback為def start_requests(self):
return [Request("http://www.zhihu.com/#signin", meta = {'cookiejar' : 1}, callback = self.post_login)]def post_login(self, response):
print 'Preparing login'
#下面這句話用于抓取請(qǐng)求網(wǎng)頁后返回網(wǎng)頁中的_xsrf字段的文字, 用于成功提交表單
xsrf = Selector(response).xpath('//input[@name="_xsrf"]/@value').extract()[0]
print xsrf
#FormRequeset.from_response是Scrapy提供的一個(gè)函數(shù), 用于post表單
#登陸成功后, 會(huì)調(diào)用after_login回調(diào)函數(shù)
return [FormRequest.from_response(response, #"http://www.zhihu.com/login",
meta = {'cookiejar' : response.meta['cookiejar']},
headers = self.headers,
formdata = {
'_xsrf': xsrf,
'email': '1527927373@qq.com',
'password': '321324jia'
},
callback = self.after_login,
dont_filter = True
)]#make_requests_from_url會(huì)調(diào)用parse,就可以與CrawlSpider的parse進(jìn)行銜接了def after_login(self, response) :
for url in self.start_urls :
yield self.make_requests_from_url(url)
理論說明如上,有不足或不懂的地方歡迎在留言區(qū)和我說明。
其次,我會(huì)寫一段爬取簡(jiǎn)書全站用戶的爬蟲來說明如何具體使用CrawlSpider
最后貼上Scrapy.spiders.CrawlSpider的源代碼,以便檢查
"""
This modules implements the CrawlSpider which is the recommended spider to use
for scraping typical web sites that requires crawling pages.
See documentation in docs/topics/spiders.rst
"""
import copyimport six
from scrapy.http import Request, HtmlResponsefrom scrapy.utils.spider import iterate_spider_outputfrom scrapy.spiders import Spider
def identity(x):
return x
class Rule(object):
def __init__(self, link_extractor, callback=None, cb_kwargs=None, follow=None, process_links=None, process_request=identity):
self.link_extractor = link_extractor
self.callback = callback
self.cb_kwargs = cb_kwargs or {}
self.process_links = process_links
self.process_request = process_request
if follow is None:
self.follow = False if callback else True
else:
self.follow = follow
class CrawlSpider(Spider):
rules = ()
def __init__(self, *a, **kw):
super(CrawlSpider, self).__init__(*a, **kw)
self._compile_rules()
def parse(self, response):
return self._parse_response(response, self.parse_start_url, cb_kwargs={}, follow=True)
def parse_start_url(self, response):
return []
def process_results(self, response, results):
return results
def _requests_to_follow(self, response):
if not isinstance(response, HtmlResponse):
return
seen = set()
for n, rule in enumerate(self._rules):
links = [lnk for lnk in rule.link_extractor.extract_links(response)
if lnk not in seen]
if links and rule.process_links:
links = rule.process_links(links)
for link in links:
seen.add(link)
r = Request(url=link.url, callback=self._response_downloaded)
r.meta.update(rule=n, link_text=link.text)
yield rule.process_request(r)
def _response_downloaded(self, response):
rule = self._rules[response.meta['rule']]
return self._parse_response(response, rule.callback, rule.cb_kwargs, rule.follow)
def _parse_response(self, response, callback, cb_kwargs, follow=True):
if callback:
cb_res = callback(response, **cb_kwargs) or ()
cb_res = self.process_results(response, cb_res)
for requests_or_item in iterate_spider_output(cb_res):
yield requests_or_item
if follow and self._follow_links:
for request_or_item in self._requests_to_follow(response):
yield request_or_item
def _compile_rules(self):
def get_method(method):
if callable(method):
return method
elif isinstance(method, six.string_types):
return getattr(self, method, None)
self._rules = [copy.copy(r) for r in self.rules]
for rule in self._rules:
rule.callback = get_method(rule.callback)
rule.process_links = get_method(rule.process_links)
rule.process_request = get_method(rule.process_request)
@classmethod
def from_crawler(cls, crawler, *args, **kwargs):
spider = super(CrawlSpider, cls).from_crawler(crawler, *args, **kwargs)
spider._follow_links = crawler.settings.getbool(
'CRAWLSPIDER_FOLLOW_LINKS', True)
return spider
def set_crawler(self, crawler):
super(CrawlSpider, self).set_crawler(crawler)
self._follow_links = crawler.settings.getbool('CRAWLSPIDER_FOLLOW_LINKS', True)
原文來自:簡(jiǎn)書/hoptop