Request 部分源碼： class Request(object_ref): 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): self._encoding = encoding # this one has to be set first self.method = str(method).upper() self._set_url(url) self._set_body(body) assert isinstance(priority, int), "Request priority not an integer: %r" % priority self.priority = priority assert callback or not errback, "Cannot use errback without a callback" self.callback = callback self.errback = errback self.cookies = cookies or {} self.headers = Headers(headers or {}, encoding=encoding) self.dont_filter = dont_filter self._meta = dict(meta) if meta else None @property def meta(self): if self._meta is None: self._meta = {} return self._meta url: 就是需要請求，并進(jìn)行下一步處理的url callback: 指定該請求返回的Response，由那個函數(shù)來處理破镰。 method: 請求一般不需要指定繁疤，默認(rèn)GET方法云芦，可設(shè)置為"GET", "POST", "PUT"等，且保證字符串大寫 headers: 請求頭 cookies: cookies,模擬用戶登錄需要指定用戶的cookies,字典dict型 meta: 比較常用，在不同的請求之間傳遞數(shù)據(jù)使用的。字典dict型 request_with_cookies = Request( url="http://www.example.com", cookies={'currency': 'USD', 'country': 'UY'}, meta={'dont_merge_cookies': True} ) encoding: 編碼類型,使用默認(rèn)的 'utf-8' 就行绒净。 dont_filter: 表明該請求不由調(diào)度器過濾。這是當(dāng)你想使用多次執(zhí)行相同的請求,忽略重復(fù)的過濾器偿衰。默認(rèn)為False挂疆。 errback: 指定錯誤處理函數(shù) ?如果希望程序執(zhí)行一開始就發(fā)送POST請求，可以重寫Spider類的start_requests(self) 方法下翎，并且不再調(diào)用start_urls里的url缤言。 class mySpider(scrapy.Spider): name = 'myspider' allow_domeas = ['renren.com'] start_urls = ["http://www.renren.com/PLogin.do"] def start_requests(self): # FormRequest 是Scrapy發(fā)送POST請求的方法 for url in self.start_urls: yield scrapy.FormRequest( url = url, formdata = {"email" : "mr_mao_hacker@163.com", "password" : "axxxxxxxe"}, callback = self.parse_page ) def parse_page(self, response): """ 請求成的回調(diào)函數(shù) """ pass Response class Response(object_ref): def __init__(self, url, status=200, headers=None, body='', 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) @property def meta(self): try: return self.request.meta except AttributeError: raise AttributeError("Response.meta not available, this response " \ "is not tied to any request") status: 響應(yīng)碼 body： 響應(yīng)體 url：響應(yīng)url self.request (request對象) self.headers　(響應(yīng)頭)