class Command(ScrapyCommand):



    requires_project = True



    def syntax(self):

        return '[options]'



    def short_desc(self):

        return 'Runs all of the spiders - My Defined'



    def run(self,args,opts):

        print('==================')

        print(type(self.crawler_process))

        spider_list = self.crawler_process.spiders.list() # 找到爬虫类



        for name in spider_list:

            print('=================')

            print(name)

            self.crawler_process.crawl(name,**opts.__dict__)



        self.crawler_process.start()

      def __init__(self, settings=None):

        if isinstance(settings, dict) or settings is None:

            settings = Settings(settings)

        self.settings = settings

        self.spider_loader = _get_spider_loader(settings) # 构造爬虫

        self._crawlers = set()

        self._active = set()

        self.bootstrap_failed = False

def _get_spider_loader(settings):



    cls_path = settings.get('SPIDER_LOADER_CLASS')

    

    # settings文件没有定义SPIDER_LOADER_CLASS，所以这里获取到的是系统的默认配置文件，

    # 默认配置文件在接下来的代码块A

    # SPIDER_LOADER_CLASS = 'scrapy.spiderloader.SpiderLoader'    

    

    loader_cls = load_object(cls_path) 

    # 这个函数就是根据路径转为类对象，也就是上面crapy.spiderloader.SpiderLoader 这个

    # 字符串变成一个类对象

    # 具体的load_object 对象代码见下面代码块B



    return loader_cls.from_settings(settings.frozencopy())

# 代码块A

#......省略若干

SCHEDULER = 'scrapy.core.scheduler.Scheduler'

SCHEDULER_DISK_QUEUE = 'scrapy.squeues.PickleLifoDiskQueue'

SCHEDULER_MEMORY_QUEUE = 'scrapy.squeues.LifoMemoryQueue'

SCHEDULER_PRIORITY_QUEUE = 'scrapy.pqueues.ScrapyPriorityQueue'



SPIDER_LOADER_CLASS = 'scrapy.spiderloader.SpiderLoader' 就是这个值

SPIDER_LOADER_WARN_ONLY = False



SPIDER_MIDDLEWARES = {}

# 代码块B 为了方便，我把异常处理的去除

from importlib import import_module #导入第三方库



def load_object(path):

    dot = path.rindex('.') 

    module, name = path[:dot], path[dot+1:]

    # 上面把路径分为基本路径+模块名

    

    mod = import_module(module)

    obj = getattr(mod, name)

    # 获取模块里面那个值

    

    return obj

In [33]: mod = import_module(module)                                                                                                                                             



In [34]: mod                                                                                                                                                                     

Out[34]: <module 'scrapy.spiderloader' from '/home/xda/anaconda3/lib/python3.7/site-packages/scrapy/spiderloader.py'>



In [35]: getattr(mod,name)                                                                                                                                                       

Out[35]: scrapy.spiderloader.SpiderLoader



In [36]: obj = getattr(mod,name)                                                                                                                                                 



In [37]: obj                                                                                                                                                                     

Out[37]: scrapy.spiderloader.SpiderLoader



In [38]: type(obj)                                                                                                                                                               

Out[38]: type

    def from_settings(cls, settings):

        return cls(settings)

class SpiderLoader(object):

    """

    SpiderLoader is a class which locates and loads spiders

    in a Scrapy project.

    """

    def __init__(self, settings):

        self.spider_modules = settings.getlist('SPIDER_MODULES') 

        # 获得settting中的模块名字，创建scrapy的时候就默认帮你生成了

        # 你可以看看你的settings文件里面的内容就可以找到这个值，是一个list

        

        self.warn_only = settings.getbool('SPIDER_LOADER_WARN_ONLY')

        self._spiders = {}

        self._found = defaultdict(list)

        self._load_all_spiders() # 加载所有爬虫

def _load_all_spiders(self):

        for name in self.spider_modules:            



                for module in walk_modules(name): # 这个遍历文件夹里面的文件，然后再转化为类对象，

                    # 保存到字典：self._spiders = {}       

                    self._load_spiders(module) # 模块变成spider



        self._check_name_duplicates() # 去重，如果名字一样就异常

def iter_spider_classes(module):

    from scrapy.spiders import Spider



    for obj in six.itervalues(vars(module)): # 找到模块里面的变量，然后迭代出来

        if inspect.isclass(obj) and \

           issubclass(obj, Spider) and \

           obj.__module__ == module.__name__ and \

           getattr(obj, 'name', None): # 有name属性，继承于Spider

           yield obj

class Command(ScrapyCommand):



    requires_project = True



    def syntax(self):

        return '[options]'



    def short_desc(self):

        return 'Runs all of the spiders - My Defined'



    def run(self,args,opts):

        print('==================')

        print(type(self.crawler_process))

        spider_list = self.crawler_process.spiders.list() # 找到爬虫类



        for name in spider_list:

            print('=================')

            print(name)

            self.crawler_process.crawl(name,**opts.__dict__)



        self.crawler_process.start()

      def __init__(self, settings=None):

        if isinstance(settings, dict) or settings is None:

            settings = Settings(settings)

        self.settings = settings

        self.spider_loader = _get_spider_loader(settings) # 构造爬虫

        self._crawlers = set()

        self._active = set()

        self.bootstrap_failed = False

def _get_spider_loader(settings):



    cls_path = settings.get('SPIDER_LOADER_CLASS')

    

    # settings文件没有定义SPIDER_LOADER_CLASS，所以这里获取到的是系统的默认配置文件，

    # 默认配置文件在接下来的代码块A

    # SPIDER_LOADER_CLASS = 'scrapy.spiderloader.SpiderLoader'    

    

    loader_cls = load_object(cls_path) 

    # 这个函数就是根据路径转为类对象，也就是上面crapy.spiderloader.SpiderLoader 这个

    # 字符串变成一个类对象

    # 具体的load_object 对象代码见下面代码块B



    return loader_cls.from_settings(settings.frozencopy())

# 代码块A

#......省略若干

SCHEDULER = 'scrapy.core.scheduler.Scheduler'

SCHEDULER_DISK_QUEUE = 'scrapy.squeues.PickleLifoDiskQueue'

SCHEDULER_MEMORY_QUEUE = 'scrapy.squeues.LifoMemoryQueue'

SCHEDULER_PRIORITY_QUEUE = 'scrapy.pqueues.ScrapyPriorityQueue'



SPIDER_LOADER_CLASS = 'scrapy.spiderloader.SpiderLoader' 就是这个值

SPIDER_LOADER_WARN_ONLY = False



SPIDER_MIDDLEWARES = {}

# 代码块B 为了方便，我把异常处理的去除

from importlib import import_module #导入第三方库



def load_object(path):

    dot = path.rindex('.') 

    module, name = path[:dot], path[dot+1:]

    # 上面把路径分为基本路径+模块名

    

    mod = import_module(module)

    obj = getattr(mod, name)

    # 获取模块里面那个值

    

    return obj

In [33]: mod = import_module(module)                                                                                                                                             



In [34]: mod                                                                                                                                                                     

Out[34]: <module 'scrapy.spiderloader' from '/home/xda/anaconda3/lib/python3.7/site-packages/scrapy/spiderloader.py'>



In [35]: getattr(mod,name)                                                                                                                                                       

Out[35]: scrapy.spiderloader.SpiderLoader



In [36]: obj = getattr(mod,name)                                                                                                                                                 



In [37]: obj                                                                                                                                                                     

Out[37]: scrapy.spiderloader.SpiderLoader



In [38]: type(obj)                                                                                                                                                               

Out[38]: type

    def from_settings(cls, settings):

        return cls(settings)

class SpiderLoader(object):

    """

    SpiderLoader is a class which locates and loads spiders

    in a Scrapy project.

    """

    def __init__(self, settings):

        self.spider_modules = settings.getlist('SPIDER_MODULES') 

        # 获得settting中的模块名字，创建scrapy的时候就默认帮你生成了

        # 你可以看看你的settings文件里面的内容就可以找到这个值，是一个list

        

        self.warn_only = settings.getbool('SPIDER_LOADER_WARN_ONLY')

        self._spiders = {}

        self._found = defaultdict(list)

        self._load_all_spiders() # 加载所有爬虫

def _load_all_spiders(self):

        for name in self.spider_modules:            



                for module in walk_modules(name): # 这个遍历文件夹里面的文件，然后再转化为类对象，

                    # 保存到字典：self._spiders = {}       

                    self._load_spiders(module) # 模块变成spider



        self._check_name_duplicates() # 去重，如果名字一样就异常

def iter_spider_classes(module):

    from scrapy.spiders import Spider



    for obj in six.itervalues(vars(module)): # 找到模块里面的变量，然后迭代出来

        if inspect.isclass(obj) and \

           issubclass(obj, Spider) and \

           obj.__module__ == module.__name__ and \

           getattr(obj, 'name', None): # 有name属性，继承于Spider

           yield obj