学Scrapy框架没有她可不行哦（爬虫）

import logging
import warnings

from scrapy import signals
from scrapy.http import Request
from scrapy.utils.trackref import object_ref
from scrapy.utils.url import url_is_from_spider
from scrapy.utils.deprecate import create_deprecated_class
from scrapy.exceptions import ScrapyDeprecationWarning
from scrapy.utils.deprecate import method_is_overridden

#所有爬虫的基类，自定义的爬虫必须从继承此类
class Spider(object_ref):

    #定义spider名字的字符串(string)。spider的名字定义了Scrapy如何定位(并初始化)spider，所以其必须是唯一的。
    #name是spider最重要的属性，而且是必须的。
    #一般做法是以该网站(domain)(加或不加 后缀 )来命名spider。例如，如果spider爬取 douban.com ，该spider通常会被命名为 douban
    name = None
    custom_settings = None

    #初始化，提取爬虫名字，start_ruls
    def __init__(self, name=None, **kwargs):
        if name is not None:
            self.name = name
        # 如果爬虫没有名字，中断后续操作则报错
        elif not getattr(self, 'name', None):
            raise ValueError("%s must have a name" % type(self).__name__)

        # python 对象或类型通过内置成员__dict__来存储成员信息
        self.__dict__.update(kwargs)

        #URL列表。当没有指定的URL时，spider将从该列表中开始进行爬取。因此，第一个被获取到的页面的URL将是该列表之一。后续的URL将会从获取到的数据中提取。
        if not hasattr(self, 'start_urls'):
            self.start_urls = []

    @property
    def logger(self):
        logger = logging.getLogger(self.name)
        return logging.LoggerAdapter(logger, {'spider': self})

    # 打印Scrapy执行后的log信息
    def log(self, message, level=log.DEBUG, **kw):
        log.msg(message, spider=self, level=level, **kw)

    @classmethod
    def from_crawler(cls, crawler, *args, **kwargs):
        spider = cls(*args, **kwargs)
        spider._set_crawler(crawler)
        return spider

    #判断对象object的属性是否存在，不存在做断言处理
    def set_crawler(self, crawler):
        assert not hasattr(self, '_crawler'), "Spider already bounded to %s" % crawler
        self._set_crawler(crawler)

    def _set_crawler(self, crawler):
        self.crawler = crawler
        self.settings = crawler.settings
        crawler.signals.connect(self.close, signals.spider_closed)

    #@property
    #def crawler(self):
    #    assert hasattr(self, '_crawler'), "Spider not bounded to any crawler"
    #    return self._crawler

    #@property
    #def settings(self):
    #    return self.crawler.settings

    #该方法将读取start_urls内的地址，并为每一个地址生成一个Request对象，交给Scrapy下载并返回Response
    #该方法仅调用一次
    def start_requests(self):
        for url in self.start_urls:
            yield self.make_requests_from_url(url)

    #start_requests()中调用，实际生成Request的函数。
    #Request对象默认的回调函数为parse()，提交的方式为get
    def make_requests_from_url(self, url):
        return Request(url, dont_filter=True)

    #默认的Request对象回调函数，处理返回的response。
    #生成Item或者Request对象。用户必须实现这个类
    def parse(self, response):
        raise NotImplementedError

    @classmethod
    def handles_request(cls, request):
        return url_is_from_spider(request.url, cls)

    @staticmethod
    def close(spider, reason):
        closed = getattr(spider, 'closed', None)
        if callable(closed):
            return closed(reason)

    def __str__(self):
        return "<%s %r at 0x%0x>" % (type(self).__name__, self.name, id(self))

    __repr__ = __str__