当前位置: 首页>>代码示例>>Python>>正文


Python frontier.FronteraScheduler类代码示例

本文整理汇总了Python中frontera.contrib.scrapy.schedulers.frontier.FronteraScheduler的典型用法代码示例。如果您正苦于以下问题:Python FronteraScheduler类的具体用法?Python FronteraScheduler怎么用?Python FronteraScheduler使用的例子?那么, 这里精选的类代码示例或许可以为您提供帮助。


在下文中一共展示了FronteraScheduler类的14个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: test_next_request_manager_finished

 def test_next_request_manager_finished(self):
     crawler = FakeCrawler()
     fs = FronteraScheduler(crawler, manager=FakeFrontierManager)
     fs.open(Spider)
     fs.frontier.manager.put_requests([fr1])
     fs.frontier.manager.finished = True
     assert fs.next_request() is None
     assert fs.stats_manager.stats.get_value('frontera/returned_requests_count') is None
开发者ID:RaoUmer,项目名称:frontera,代码行数:8,代码来源:test_frontera_scheduler.py

示例2: test_next_request

 def test_next_request(self):
     crawler = FakeCrawler()
     fs = FronteraScheduler(crawler, manager=FakeFrontierManager)
     fs.open(Spider)
     fs.frontier.manager.put_requests([fr1, fr2, fr3])
     requests = [fs.next_request() for _ in range(3)]
     assert set([request.url for request in requests]) == set([fr1.url, fr2.url, fr3.url])
     assert all([isinstance(request, Request) for request in requests])
     assert fs.stats_manager.stats.get_value('frontera/returned_requests_count') == 3
开发者ID:RaoUmer,项目名称:frontera,代码行数:9,代码来源:test_frontera_scheduler.py

示例3: test_redirect_disabled_enqueue_requests

 def test_redirect_disabled_enqueue_requests(self):
     settings = Settings()
     settings['REDIRECT_ENABLED'] = False
     crawler = FakeCrawler(settings)
     fs = FronteraScheduler(crawler, manager=FakeFrontierManager)
     fs.open(Spider)
     assert fs.enqueue_request(rr1) is False
     assert fs.enqueue_request(rr2) is False
     assert fs.enqueue_request(rr3) is False
开发者ID:scrapinghub,项目名称:frontera,代码行数:9,代码来源:test_frontera_scheduler.py

示例4: test_enqueue_requests

 def test_enqueue_requests(self):
     crawler = FakeCrawler()
     fs = FronteraScheduler(crawler, manager=FakeFrontierManager)
     fs.open(Spider)
     assert fs.enqueue_request(r1) is True
     assert fs.enqueue_request(r2) is True
     assert fs.enqueue_request(r3) is True
     assert set(seed.url for seed in fs.frontier.manager.seeds) == set([r1.url, r2.url, r3.url])
     assert all([isinstance(seed, FRequest) for seed in fs.frontier.manager.seeds])
     assert fs.stats_manager.stats.get_value('frontera/seeds_count') == 3
开发者ID:RaoUmer,项目名称:frontera,代码行数:10,代码来源:test_frontera_scheduler.py

示例5: test_redirect_enabled_enqueue_requests

 def test_redirect_enabled_enqueue_requests(self):
     settings = Settings()
     settings['REDIRECT_ENABLED'] = True
     crawler = FakeCrawler(settings)
     fs = FronteraScheduler(crawler, manager=FakeFrontierManager)
     fs.open(Spider)
     assert fs.enqueue_request(rr1) is True
     assert fs.enqueue_request(rr2) is True
     assert fs.enqueue_request(rr3) is True
     assert set([request.url for request in fs._pending_requests]) == set([rr1.url, rr2.url, rr3.url])
开发者ID:scrapinghub,项目名称:frontera,代码行数:10,代码来源:test_frontera_scheduler.py

示例6: test_process_exception

 def test_process_exception(self):
     exception = type('exception', (object,), {})
     crawler = FakeCrawler()
     fs = FronteraScheduler(crawler, manager=FakeFrontierManager)
     fs.open(Spider)
     fs.process_exception(r1, exception(), Spider)
     error = fs.frontier.manager.errors.pop()
     assert error[0].url == r1.url
     assert error[1] == 'exception'
     assert fs.stats_manager.stats.get_value('frontera/request_errors_count') == 1
     assert fs.stats_manager.stats.get_value('frontera/request_errors_count/exception') == 1
开发者ID:RaoUmer,项目名称:frontera,代码行数:11,代码来源:test_frontera_scheduler.py

示例7: test_redirect_disabled_enqueue_requests

 def test_redirect_disabled_enqueue_requests(self):
     settings = Settings()
     settings['REDIRECT_ENABLED'] = False
     crawler = FakeCrawler(settings)
     fs = FronteraScheduler(crawler, manager=FakeFrontierManager)
     fs.open(Spider)
     assert fs.enqueue_request(rr1) is False
     assert fs.enqueue_request(rr2) is False
     assert fs.enqueue_request(rr3) is True
     assert isinstance(fs.frontier.manager.seeds[0], FRequest)
     assert len(fs.frontier.manager.seeds) == 1
     assert fs.frontier.manager.seeds[0].url == rr3.url
     assert fs.stats_manager.stats.get_value('frontera/seeds_count') == 1
开发者ID:RaoUmer,项目名称:frontera,代码行数:13,代码来源:test_frontera_scheduler.py

示例8: test_redirect_enabled_enqueue_requests

 def test_redirect_enabled_enqueue_requests(self):
     settings = Settings()
     settings['REDIRECT_ENABLED'] = True
     crawler = FakeCrawler(settings)
     fs = FronteraScheduler(crawler, manager=FakeFrontierManager)
     fs.open(Spider)
     assert fs.enqueue_request(rr1) is True
     assert fs.enqueue_request(rr2) is True
     assert fs.enqueue_request(rr3) is True
     assert len(fs.frontier.manager.seeds) == 1
     assert isinstance(fs.frontier.manager.seeds[0], FRequest)
     assert fs.frontier.manager.seeds[0].url == rr3.url
     assert set([request.url for request in fs._pending_requests]) == set([rr1.url, rr2.url])
     assert all([isinstance(request, Request) for request in fs._pending_requests])
     assert fs.stats_manager.stats.get_value('frontera/seeds_count') == 1
     assert fs.stats_manager.stats.get_value('frontera/redirected_requests_count') == 2
开发者ID:RaoUmer,项目名称:frontera,代码行数:16,代码来源:test_frontera_scheduler.py

示例9: test_process_spider_output

 def test_process_spider_output(self):
     i1 = {'name': 'item', 'item': 'i1'}
     i2 = {'name': 'item', 'item': 'i2'}
     result = [r1, r2, r3, i1, i2]
     resp = Response(fr1.url, request=Request(fr1.url, meta={'frontier_request': fr1}))
     crawler = FakeCrawler()
     fs = FronteraScheduler(crawler, manager=FakeFrontierManager)
     fs.open(Spider)
     assert sorted(list(fs.process_spider_output(resp, result, Spider))) == sorted([i1, i2])
     assert isinstance(fs.frontier.manager.responses[0], FResponse)
     assert fs.frontier.manager.responses[0].url == resp.url
     assert set([request.url for request in fs.frontier.manager.links]) == set([r1.url, r2.url, r3.url])
     assert all([isinstance(request, FRequest) for request in fs.frontier.manager.links])
     assert fs.stats_manager.stats.get_value('frontera/crawled_pages_count') == 1
     assert fs.stats_manager.stats.get_value('frontera/crawled_pages_count/200') == 1
     assert fs.stats_manager.stats.get_value('frontera/links_extracted_count') == 3
开发者ID:RaoUmer,项目名称:frontera,代码行数:16,代码来源:test_frontera_scheduler.py

示例10: test_next_request_overused_keys_info

 def test_next_request_overused_keys_info(self):
     settings = Settings()
     settings['CONCURRENT_REQUESTS_PER_DOMAIN'] = 0
     settings['CONCURRENT_REQUESTS_PER_IP'] = 5
     crawler = FakeCrawler(settings)
     # the keys in the slot_dict are ip's, the first value in the pair is the
     # slot.active list(only it's length is needed) and the second value is slot.concurrency.
     slot_dict = {'1.2.3': ([0]*3, 1), '2.1.3': ([0]*30, 2), '3.2.2': ([0]*5, 1), '4.1.3': ([0]*110, 20)}
     crawler.set_slots(slot_dict)
     fs = FronteraScheduler(crawler, manager=FakeFrontierManager)
     fs.open(Spider)
     fs.frontier.manager.put_requests([fr1])
     request = fs.next_request()
     assert request.url == fr1.url
     assert isinstance(request, Request)
     assert fs.frontier.manager.get_next_requests_kwargs[0]['key_type'] == 'ip'
     assert set(fs.frontier.manager.get_next_requests_kwargs[0]['overused_keys']) == set(['2.1.3', '4.1.3'])
     assert fs.stats_manager.stats.get_value('frontera/returned_requests_count') == 1
开发者ID:RaoUmer,项目名称:frontera,代码行数:18,代码来源:test_frontera_scheduler.py

示例11: test_process_spider_output

 def test_process_spider_output(self):
     i1 = {"name": "item", "item": "i1"}
     i2 = {"name": "item", "item": "i2"}
     result = [r1, r2, r3, i1, i2]
     resp = Response(fr1.url, request=Request(fr1.url, meta={b"frontier_request": fr1}))
     crawler = FakeCrawler()
     fs = FronteraScheduler(crawler, manager=FakeFrontierManager)
     fs.open(Spider)
     assert sorted(list(fs.process_spider_output(resp, result, Spider)), key=lambda i: sorted(i["item"])) == sorted(
         [i1, i2], key=lambda i: sorted(i["item"])
     )
     assert isinstance(fs.frontier.manager.responses[0], FResponse)
     assert fs.frontier.manager.responses[0].url == resp.url
     assert set([request.url for request in fs.frontier.manager.links]) == set([r1.url, r2.url, r3.url])
     assert all([isinstance(request, FRequest) for request in fs.frontier.manager.links])
     assert fs.stats_manager.stats.get_value("frontera/crawled_pages_count") == 1
     assert fs.stats_manager.stats.get_value("frontera/crawled_pages_count/200") == 1
     assert fs.stats_manager.stats.get_value("frontera/links_extracted_count") == 3
开发者ID:voith,项目名称:frontera,代码行数:18,代码来源:test_frontera_scheduler.py

示例12: test_close

 def test_close(self):
     crawler = FakeCrawler()
     fs = FronteraScheduler(crawler, manager=FakeFrontierManager)
     fs.open(Spider)
     fs.frontier.manager.put_requests([fr1, fr2, fr3])
     fs.next_request()
     fs.frontier.manager.iteration = 5
     fs.close('reason')
     assert fs.frontier.manager._stopped is True
     assert fs.stats_manager.stats.get_value('frontera/pending_requests_count') == 2
     assert fs.stats_manager.stats.get_value('frontera/iterations') == 5
开发者ID:RaoUmer,项目名称:frontera,代码行数:11,代码来源:test_frontera_scheduler.py

示例13: test_process_spider_output

    def test_process_spider_output(self):
        i1 = {'name': 'item', 'item': 'i1'}
        i2 = {'name': 'item', 'item': 'i2'}
        items = [i1 , i2]
        requests = [r1, r2, r3]
        result = list(requests)
        result.extend(items)
        resp = Response(fr1.url, request=Request(fr1.url, meta={b'frontier_request': fr1}))
        crawler = FakeCrawler()
        fs = FronteraScheduler(crawler, manager=FakeFrontierManager)
        spider = Spider(name="testing")
        fs.open(spider)
        out_items = list(fs.process_spider_output(resp, result, spider))
        assert len(out_items) == len(items)
        assert set([r.url for r in fs.frontier.manager.links]) == set([r.url for r in requests])

        assert isinstance(fs.frontier.manager.responses[0], FResponse)
        assert fs.frontier.manager.responses[0].url == resp.url
        assert set([request.url for request in fs.frontier.manager.links]) == set([r1.url, r2.url, r3.url])
        assert all([isinstance(request, FRequest) for request in fs.frontier.manager.links])
        assert fs.stats_manager.stats.get_value('frontera/crawled_pages_count') == 1
        assert fs.stats_manager.stats.get_value('frontera/crawled_pages_count/200') == 1
        assert fs.stats_manager.stats.get_value('frontera/links_extracted_count') == 3
开发者ID:scrapinghub,项目名称:frontera,代码行数:23,代码来源:test_frontera_scheduler.py

示例14: test_process_spider_output

 def test_process_spider_output(self):
     i1 = {'name': 'item', 'item': 'i1'}
     i2 = {'name': 'item', 'item': 'i2'}
     no_requests = 3
     result = [r1, r2, r3, i1, i2]
     resp = Response(fr1.url, request=Request(fr1.url, meta={b'frontier_request': fr1}))
     crawler = FakeCrawler()
     fs = FronteraScheduler(crawler, manager=FakeFrontierManager)
     fs.open(Spider)
     out = list(fs.process_spider_output(resp, result, Spider))
     assert len(out) == len(result)
     out_request = out[:no_requests]
     assert set(r.url for r in out_request) == set(r.url for r in result[:no_requests])
     out_items = out[no_requests:]
     assert sorted(out_items, key=lambda i: sorted(i['item'])) == \
         sorted([i1, i2], key=lambda i: sorted(i['item']))
     assert isinstance(fs.frontier.manager.responses[0], FResponse)
     assert fs.frontier.manager.responses[0].url == resp.url
     assert set([request.url for request in fs.frontier.manager.links]) == set([r1.url, r2.url, r3.url])
     assert all([isinstance(request, FRequest) for request in fs.frontier.manager.links])
     assert fs.stats_manager.stats.get_value('frontera/crawled_pages_count') == 1
     assert fs.stats_manager.stats.get_value('frontera/crawled_pages_count/200') == 1
     assert fs.stats_manager.stats.get_value('frontera/links_extracted_count') == 3
开发者ID:Preetwinder,项目名称:frontera,代码行数:23,代码来源:test_frontera_scheduler.py


注:本文中的frontera.contrib.scrapy.schedulers.frontier.FronteraScheduler类示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。