0
Я пытаюсь использовать инструмент python scrapy для извлечения информации с сайта bitcointalk.org о пользователях и открытых ключах, которые они публикуют на форуме для пожертвования.Объект ответа на атрибут атрибута doesnot имеет атрибут 'text'
Я нашел этот кусок кода онлайн, внеся изменения в него, чтобы он работал на моем желаемом веб-сайте, но я столкнулся с ошибкой. Объект ответа атрибута AttributeError не имеет текста атрибута.
Ниже приведен код для справки
class BitcointalkSpider(CrawlSpider):
name = "bitcointalk"
allowed_domains = ["bitcointalk.org"]
start_urls = ["https://bitcointalk.org/index.php"]
rules = (
Rule(SgmlLinkExtractor(deny=[
'https://bitcointalk\.org/index\.php\?action=ignore',
'https://bitcointalk\.org/index\.php\?action=profile',
],
allow_domains='bitcointalk.org'), callback='parse_item', follow=True),
)
def parse_item(self, response):
sel = Selector(response)
sites = sel.xpath('//tr[contains(@class, "td_headerandpost")]')
items = []
for site in sites:
item = BitcoinItem()
item["membername"] = site.xpath('.//td[@class="poster_info"]/b/a/text()').extract()
addresses = site.xpath('.//div[contains(@class, "signature")]/text()').re(r'(1[1-9A-HJ-NP-Za-km-z]{26,33})')
if item["membername"] and addresses:
addr_list = set()
for addr in addresses:
if (bcv.check_bc(addr)):
addr_list.add(addr)
item["address"] = addr_list
if len(addr_list) > 0:
items.append(item)
return items
и ошибка, что я получаю это:
Traceback (most recent call last):
File "/usr/local/lib/python2.7/dist-packages/scrapy/utils/defer.py", line 102, in iter_errback
yield next(it)
File "/usr/local/lib/python2.7/dist-packages/scrapy/spidermiddlewares/offsite.py", line 29, in process_spider_output
for x in result:
File "/usr/local/lib/python2.7/dist-packages/scrapy/spidermiddlewares/referer.py", line 22, in <genexpr>
return (_set_referer(r) for r in result or())
File "/usr/local/lib/python2.7/dist-packages/scrapy/spidermiddlewares/urllength.py", line 37, in <genexpr>
return (r for r in result or() if _filter(r))
File "/usr/local/lib/python2.7/dist-packages/scrapy/spidermiddlewares/depth.py", line 58, in <genexpr>
return (r for r in result or() if _filter(r))
File "/usr/local/lib/python2.7/dist-packages/scrapy/spiders/crawl.py", line 72, in _parse_response
cb_res = callback(response, **cb_kwargs) or()
File "/home/sunil/Desktop/Nikhil/Thesis/mit_bitcoin/bitcoin/spiders/bitcointalk_spider.py", line 24, in parse_item
sel = Selector(response)
File "/usr/local/lib/python2.7/dist-packages/scrapy/selector/unified.py", line 63, in __init__
text = response.text
AttributeError: 'Response' object has no attribute 'text'