python3_scrapy_Scrapy类方法及属性剖析

scrapy包Scrapy类方法及属性剖析

"""
Base class for Scrapy spiders

See documentation in docs/topics/spiders.rst
"""
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


# 1.所有爬虫的基类，用户定义的爬虫必需从这个类继承
class Spider(object_ref):

	# 2.spider名字定义了Scrapy如何定位(并初始化)spider，所以其必需是唯一的，且是必需的属性
    name = None
    custom_settings = None

	# 3.初始化，提取爬虫名字、start_urls
    def __init__(self, name=None, **kwargs):
        if name is not None:
            self.name = name
		
		# 4.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__)
			
		# 5.python对象或类型通过内置成员__dict__来存储成员信息
        self.__dict__.update(kwargs)
		
		# 6.URL列表。当没有指定URL时，spider将从该列表中进行爬取
        if not hasattr(self, 'start_urls'):
            self.start_urls = []

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

	# 7.打印Scrapy执行后的log信息
	# 使用scrapy.log.msg()方法记录(log)message。
    def log(self, message, level=logging.DEBUG, **kw):
        self.logger.log(level, message, **kw)

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

	# 8.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):
        warnings.warn("set_crawler is deprecated, instantiate and bound the "
                      "spider to this crawler with from_crawler method "
                      "instead.",
                      category=ScrapyDeprecationWarning, stacklevel=2)
        assert not hasattr(self, 'crawler'), "Spider already bounded to a " \
                                             "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)

	# 9.该方法读取start_urls内的地址，并为每一个地址生成Request对象，交给Scrapy下载并返回Response。
	# 9.该方法仅被调用一次
    def start_requests(self):
        cls = self.__class__
        if method_is_overridden(cls, Spider, 'make_requests_from_url'):
            warnings.warn(
                "Spider.make_requests_from_url method is deprecated; it "
                "won't be called in future Scrapy releases. Please "
                "override Spider.start_requests method instead (see %s.%s)." % (
                    cls.__module__, cls.__name__
                ),
            )
            for url in self.start_urls:
                yield self.make_requests_from_url(url)
        else:
            for url in self.start_urls:
                yield Request(url, dont_filter=True)

	# 10.9中方法调用(当指定了URL时)，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):
        """ This method is deprecated. """
		# dont_filter=True默认不做去重操作
        return Request(url, dont_filter=True)

	# 11.默认的Request对象回调函数，处理返回的response
	# 11.生成item或者Request对象
	# 11.默认什么也不做。在子类中必需重写该方法，负责解析返回的网页数据，提取结构化数据
    def parse(self, response):
        raise NotImplementedError('{}.parse callback is not defined'.format(self.__class__.__name__))

    @classmethod
    def update_settings(cls, settings):
        settings.setdict(cls.custom_settings or {}, priority='spider')

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

	# 12.当spider关闭时，该函数被调用。该方法提供了一个替代调用signals.connect()来监听spider_closed信号的快捷方式	
    @staticmethod
    def close(spider, reason):
        closed = getattr(spider, 'closed', None)
        if callable(closed):
            return closed(reason)

	# 13.返回爬虫对象的详细信息(类型、爬虫名称、爬虫ID)
    def __str__(self):
        return "<%s %r at 0x%0x>" % (type(self).__name__, self.name, id(self))

    __repr__ = __str__


BaseSpider = create_deprecated_class('BaseSpider', Spider)


class ObsoleteClass(object):
    def __init__(self, message):
        self.message = message

    def __getattr__(self, name):
        raise AttributeError(self.message)

spiders = ObsoleteClass(
    '"from scrapy.spider import spiders" no longer works - use '
    '"from scrapy.spiderloader import SpiderLoader" and instantiate '
    'it with your project settings"'
)

# Top-level imports
from scrapy.spiders.crawl import CrawlSpider, Rule
from scrapy.spiders.feed import XMLFeedSpider, CSVFeedSpider
from scrapy.spiders.sitemap import SitemapSpider