def post_request(url, seq, seq_no):
body = get_body(seq, seq_no)
r = requests.post(url, data=body)
#print("Request status: ", r.status_code, r.reason)
p = html_parser.Parser(r.text)
result = p.pars_html()
return result
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):
# 初始化url调度器
self.urls = url_manager.UrlManager()
# 初始化下载器
self.downloader = html_downloader.HtmlDownloader()
# 初始化解析器
self.parser = html_parser.Parser()
# 内容输出器
self.outputer = html_outputer.HtmlOutputer()
# 内容存储器
self.saver = db_saver.DBSaver()
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, url):
self.urls = url_manager.UrlManager()
self.downloader = html_downloader.HtmlDownloader()
self.parser = html_parser.Parser(url)
self.outputer = outputer.Outputer()
self.root_url = url
def __init__(self):
self.parser = html_parser.Parser()
self.output = html_output.Output()
def parser_factory(type, settings):
if html_parser.TYPE_HTML == type:
return html_parser.Parser(settings)
def __init__(self):
self.urls = url_manager.UrlManager()
self.downloader = page_downloader.Downloader()
self.parser = html_parser.Parser()
self.outputers = outputer.Outputer()
def parse_race_as_html(self):
print('Parsing race as html')
self.html_parser = html_parser.Parser(self.racename, debug=True)
self.race = self.html_parser.parse_page()
self.html_parser.quit()