"""
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 copy
import six
from scrapy.http import Request, HtmlResponse
from scrapy.utils.spider import iterate_spider_output
from scrapy.spiders import Spider
def identity(x): #process_request默认方法,什么也没做
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 #处理url的方法
self.process_request = process_request #处理请求的方法,默认是什么也没做
if follow is None: #如果follow没有指定的情况下,使用call贩判断
self.follow = False if callback else True #有callback的时候默认为False,没有默认为True
else:
self.follow = follow #否则根据follow的值来判断
class CrawlSpider(Spider):
rules = ()
def __init__(self, *a, **kw):
super(CrawlSpider, self).__init__(*a, **kw)
self._compile_rules()
def parse(self, response): #这里最开始处理start_url你的响应,之后会处理其他的响应
return self._parse_response(response, self.parse_start_url, cb_kwargs={}, follow=True)
def parse_start_url(self, response): #默认该方法求也没干
return []
def process_results(self, response, results): #默认该方法求也没干
return results
def _build_request(self, rule, link): #构造一个请求
#普通的请求,和我们scrapy.Request一样的
r = Request(url=link.url, callback=self._response_downloaded) #构造一个请求,默认respsne交给_response_downloaded处理
#添加一些其他信息进去
r.meta.update(rule=rule, link_text=link.text)
return r
def _requests_to_follow(self, response):
if not isinstance(response, HtmlResponse):
return
seen = set()
for n, rule in enumerate(self._rules): #继续开始提取url了
links = [lnk for lnk in rule.link_extractor.extract_links(response)
if lnk not in seen]
if links and rule.process_links: #如果我们在Rule你面设置process_links方法的话,会用该方法处理一下url地址再使用
links = rule.process_links(links)
#到这里reponse中经过链接提取器提取的url都拿到了
for link in links:
seen.add(link) #简单的使用了一个set过滤
r = self._build_request(n, link) #构造的一个请求
yield rule.process_request(r) #发送了一个请求,默认情况下process_request什么也没干
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 () #默认情况下什么也没干,因为默认start_urls是没callback的,见上面的parse_start_url
print(cb_res,"*"*100)
cb_res = self.process_results(response, cb_res) #默认情况下什也没做
print(cb_res,"-"*100)
for requests_or_item in iterate_spider_output(cb_res): #转化为可迭代对象,但是默认ca_res是空的
yield requests_or_item
if follow and self._follow_links: #
#start_url的默认follow为True,所以该条件成立
print("self._follow_links",self._follow_links)
for request_or_item in self._requests_to_follow(response):
print(request_or_item,"="*100)
yield request_or_item #发送了一个请求,
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)
#这个地方有个全局的默认设置,可以在setting中配置,默认为True
self._follow_links = crawler.settings.getbool('CRAWLSPIDER_FOLLOW_LINKS', True)
