Я делаю гусеничный ход с помощью скрапа и не могу использовать слово «Правило», но я импортировал его.
stack_crawler.py
import scrapy
from scrapy.contrib.linkextractors import LinkExtractor
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.selector import Selector
from scrapy.item import Item
from stack.items import StackItem
class StackCrawlerSpider(CrawlSpider):
name = 'stack_crawler'
allowed_domains = ['stackoverflow.com']
start_urls = ['http://www.stackoverflow.com/']
rules = (Rule(LinkExtractor(allow=r'Items/'), callback='parse_item', follow=True),
)
...
когда я выполню
Таким образом, я получаю это сообщение об ошибке в оболочке «NameError: имя« Правило »не определено»
Кто-нибудь может мне помочь?
(ENV) lucas@lucas-TWS:~/ENV/stack$ scrapy crawl stack_crawler
/home/lucas/ENV/stack/stack/spiders/stack_crawler.py:3: ScrapyDeprecationWarning: Module `scrapy.contrib.linkextractors` is deprecated, use `scrapy.linkextractors` instead
from scrapy.contrib.linkextractors import LinkExtractor
/home/lucas/ENV/stack/stack/spiders/stack_crawler.py:4: ScrapyDeprecationWarning: Module `scrapy.contrib.spiders` is deprecated, use `scrapy.spiders` instead
from scrapy.contrib.spiders import CrawlSpider, Rule
/home/lucas/ENV/stack/stack/spiders/stack_crawler.py:5: ScrapyDeprecationWarning: Module `scrapy.contrib.linkextractors.sgml` is deprecated, use `scrapy.linkextractors.sgml` instead
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
/home/lucas/ENV/stack/stack/spiders/stack_crawler.py:18: ScrapyDeprecationWarning: SgmlLinkExtractor is deprecated and will be removed in future releases. Please use scrapy.linkextractors.LinkExtractor
Rule(SgmlLinkExtractor(allow=r'questions\?page=[0-9]&sort=newest'),
Traceback (most recent call last):
File "/usr/local/bin/scrapy", line 11, in <module>
sys.exit(execute())
File "/usr/local/lib/python2.7/dist-packages/scrapy/cmdline.py", line 149, in execute
cmd.crawler_process = CrawlerProcess(settings)
File "/usr/local/lib/python2.7/dist-packages/scrapy/crawler.py", line 249, in __init__
super(CrawlerProcess, self).__init__(settings)
File "/usr/local/lib/python2.7/dist-packages/scrapy/crawler.py", line 137, in __init__
self.spider_loader = _get_spider_loader(settings)
File "/usr/local/lib/python2.7/dist-packages/scrapy/crawler.py", line 336, in _get_spider_loader
return loader_cls.from_settings(settings.frozencopy())
File "/usr/local/lib/python2.7/dist-packages/scrapy/spiderloader.py", line 61, in from_settings
return cls(settings)
File "/usr/local/lib/python2.7/dist-packages/scrapy/spiderloader.py", line 25, in __init__
self._load_all_spiders()
File "/usr/local/lib/python2.7/dist-packages/scrapy/spiderloader.py", line 47, in _load_all_spiders
for module in walk_modules(name):
File "/usr/local/lib/python2.7/dist-packages/scrapy/utils/misc.py", line 71, in walk_modules
submod = import_module(fullpath)
File "/usr/lib/python2.7/importlib/__init__.py", line 37, in import_module
__import__(name)
File "/home/lucas/ENV/stack/stack/spiders/stack_spider.py", line 7, in <module>
class StackSpider(Spider):
File "/home/lucas/ENV/stack/stack/spiders/stack_spider.py", line 15, in StackSpider
Rule(LinkExtractor(allow=r'questions\?page=[0-2]&sort=newest'),
NameError: name 'Rule' is not defined