Scrapy源码分析（四）：请求Request

本次我们要分析的Scrapy源码为Request模块，模块的位置：

from scrapytest.http import Request

首先把Request的源码附上：

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 设定了request使用的编码
        self.method = str(method).upper()     #GET POST等等
        self._set_url(url)      #调用URL处理函数，设置url属性
        self._set_body(body)      #设置Body属性
        assert isinstance(priority, int), "Request priority not an integer: %r" % priority #检查priority是否int
        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              #将meta作为一个属性
    def meta(self):
        if self._meta is None:
            self._meta = {}
        return self._meta

    def _get_url(self):
        return self._url

    def _set_url(self, url):           #设置url，输入要字符型的
        if not isinstance(url, six.string_types):
            raise TypeError('Request url must be str or unicode, got %s:' % type(url).__name__)

        s = safe_url_string(url, self.encoding)       #Urlencode
        self._url = escape_ajax(s)              #处理!#

        if ':' not in self._url:           #要有http://或者https://
            raise ValueError('Missing scheme in request url: %s' % self._url)

    url = property(_get_url, obsolete_setter(_set_url, 'url'))     #将url设置为一个只读属性，修改url要通过.replace实现

    def _get_body(self):
        return self._body

    def _set_body(self, body):
        if body is None:
            self._body = b''       #b''在py2.7中与普通字符串型一致，为了兼容py3
        else:
            self._body = to_bytes(body, self.encoding) #将unicode型转为utf-8等等byte类型

    body = property(_get_body, obsolete_setter(_set_body, 'body')) #body也是只读属性，修改要通过replace

    @property
    def encoding(self):
        return self._encoding

    def __str__(self):
        return "<%s %s>" % (self.method, self.url)

    __repr__ = __str__

    def copy(self):
        """Return a copy of this Request"""
        return self.replace()

    def replace(self, *args, **kwargs):  #创建一个新的Request对象，对于新给的kwargs，使用新的，没给的使用原有对象的
        """Create a new Request with the same attributes except for those
        given new values.
        """
        for x in ['url', 'method', 'headers', 'body', 'cookies', 'meta',
                  'encoding', 'priority', 'dont_filter', 'callback', 'errback']:
            kwargs.setdefault(x, getattr(self, x))
        cls = kwargs.pop('cls', self.__class__)
        return cls(*args, **kwargs)

下面我们来逐个函数分析：

    def __init__(self, url, callback=None, method='GET', headers=None, body=None,
                 cookie