def __init__(self):
self.manager = Manager.Manager()
self.downloader = html_downloader.Downloader()
self.saver = html_saver.Saver()
self.parser = html_parser.Parser(self.manager)
self.manager.add_one_url("https://book.douban.com/")
#self.manager.add_one_url("https://www.baidu.com/")
self.limits = 100
def __init__(self):
# 初始化爬虫的管理器
self.manager = url_manager.UrlManager()
# 初始化输出器
self.outputer = html_outputer.Outputer()
# 初始化解析器
self.parser = html_parser.Parser()
# 初始化下载器
self.downloader = html_downloader.Downloader()
def __init__(self):
self.url = url_manager.UrlManager()
self.downloader = html_downloader.Downloader()
self.parser = html_parser.Parser()
self.generator = html_generator.Generator()
def __init__(self): # object 和 self 是什么关系？
self.urls = url_manager.Manager() # 文件名（库名）.类？
self.download = html_downloader.Downloader()
self.parser = html_parser.Parser()
self.output = html_outputer.Outputer()
def __init__(self):
self.downloader = html_downloader.Downloader()
self.parser = html_parser.HtmlParser()
self.outputer = json_outputer.JsonOutputer()
def __init__(self):
# 初始化URL管理器，下载器，解析器，输出器
self.urls = url_manager.UrlManager()
self.downloader = html_downloader.Downloader()
self.parser = html_parser.Htmlparser()
self.outputer = html_outputer.Htmloutputer()