scrapy进阶开发（一）：scrapy架构源码分析

    ...
    ...
    
    # 此处为执行过程中1-2步，Engine拿到request后发送给Scheduler
    def schedule(self, request, spider):
        self.signals.send_catch_log(signal=signals.request_scheduled,
                request=request, spider=spider)
        # 调用scheduler的enqueue_request方法将request放到Scheduler中
        if not  self.slot.scheduler.enqueue_request(request):
            self.signals.send_catch_log(signal=signals.request_dropped,
                                        request=request, spider=spider)
    ...
    ...
    # 此处为执行过程中第三步，从Engine中拿request给Scheduler
    def _next_request_from_scheduler(self, spider):
        slot = self.slot
        request = slot.scheduler.next_request()
        # 爬虫首次启动的时候先执行这个_next_request_from_scheduler方法，
        # 但是scheduler里此时没有request，所以就会去从Spider中读取start_urls
        if not request:
            return
        d = self._download(request, spider)
        d.addBoth(self._handle_downloader_output, request, spider)
        d.addErrback(lambda f: logger.info('Error while handling downloader output',
                                           exc_info=failure_to_exc_info(f),
                                           extra={'spider': spider}))
        d.addBoth(lambda _: slot.remove_request(request))
        d.addErrback(lambda f: logger.info('Error while removing request from slot',
                                           exc_info=failure_to_exc_info(f),
                                           extra={'spider': spider}))
        d.addBoth(lambda _: slot.nextcall.schedule())
        d.addErrback(lambda f: logger.info('Error while scheduling new request',
                                           exc_info=failure_to_exc_info(f),
                                           extra={'spider': spider}))
        return d
    ...
    ...

class Request(object_ref):
    # url： 请求参数
    # callback：请求回调函数
    # method： http请求类型
    # headers： 请求头
    # body：请求体
    # cookies：浏览器cookie，自动登录后，scrapy会自动把cookie加入request中
    # 该操作的实现是由scrapy.downloadermiddlewares.cookies.CookiesMiddleware的scrapy内置Middleware完成的
    # meta：元信息，（可以在Request中传递）
    # encoding：网页编码格式，默认UTF-8
    # priority：设置在scheduler的调度优先级
    # dont_filter：是否不过滤同时发出的相同request请求
    # errback：失败的回调函数
    # 
    def __init__(self, url, callback=None, method='GET', headers=None, body=None,
                     cookies=None, meta=None, encoding='utf-8', priority=0,
                     dont_filter=False, errback=None, flags=None):

class Response(object_ref):

    # url 网页的url
    # status 返回状态码，默认是200，代表成功
    # headers 服务器返回的响应头
    # body 返回的内容体
    # request 之前yield的Request，对应的请求
    def __init__(self, url, status=200, headers=None, body=b'', flags=None, request=None):
        self.headers = Headers(headers or {})
        self.status = int(status)
        self._set_body(body)
        self._set_url(url)
        self.request = request
        self.flags = [] if flags is None else list(flags)

from scrapy.http.response.text import TextResponse

class HtmlResponse(TextResponse):
    pass

class TextResponse(Response):
    ...
    ...
    # Response内部已经引入了selector拱xpath,css方法调用
    @property
    def selector(self):
        from scrapy.selector import Selector
        if self._cached_selector is None:
            self._cached_selector = Selector(self)
        return self._cached_selector

    # xpath 选择器
    def xpath(self, query, **kwargs):
        return self.selector.xpath(query, **kwargs)

    # css 选择器
    def css(self, query):
        return self.selector.css(query)
    ...
    ...