Я модифицировал этого паука, но он выдает эти ошибки
Gave up retrying <GET https://lib.maplelegends.com/robots.txt> (failed 3 times): 503 Service Unavailable
2019-01-06 23:43:56 [scrapy.core.engine] DEBUG: Crawled (503) <GET https://lib.maplelegends.com/robots.txt> (referer: None)
2019-01-06 23:43:56 [scrapy.downloadermiddlewares.retry] DEBUG: Retrying <GET https://lib.maplelegends.com/?p=etc&id=4004003> (failed 1 times): 503 Service Unavailable
2019-01-06 23:43:56 [scrapy.downloadermiddlewares.retry] DEBUG: Retrying <GET https://lib.maplelegends.com/?p=etc&id=4004003> (failed 2 times): 503 Service Unavailable
2019-01-06 23:43:56 [scrapy.downloadermiddlewares.retry] DEBUG: Gave up retrying <GET https://lib.maplelegends.com/?p=etc&id=4004003> (failed 3 times): 503 Service Unavailable
2019-01-06 23:43:56 [scrapy.core.engine] DEBUG: Crawled (503) <GET https://lib.maplelegends.com/?p=etc&id=4004003> (referer: None)
2019-01-06 23:43:56 [scrapy.spidermiddlewares.httperror] INFO: Ignoring response <503 https://lib.maplelegends.com/?p=etc&id=4004003>: HTTP status code is not handled or not allowed
Код сканера:
#!/usr/bin/env python3
import scrapy
import time
start_url = 'https://lib.maplelegends.com/?p=etc&id=4004003'
class MySpider(scrapy.Spider):
name = 'MySpider'
start_urls = [start_url]
def parse(self, response):
# print('url:', response.url)
products = response.xpath('.//div[@class="table-responsive"]/table/tbody')
for product in products:
item = {
#'name': product.xpath('./tr/td/b[1]/a/text()').extract(),
'link': product.xpath('./tr/td/b[1]/a/@href').extract(),
}
# url = response.urljoin(item['link'])
# yield scrapy.Request(url=url, callback=self.parse_product, meta={'item': item})
yield response.follow(item['link'], callback=self.parse_product, meta={'item': item})
time.sleep(5)
# execute with low
yield scrapy.Request(start_url, dont_filter=True, priority=-1)
def parse_product(self, response):
# print('url:', response.url)
# name = response.xpath('(//strong)[1]/text()').re(r'(\w+)')
hp = response.xpath('//*[contains(concat( " ", @class, " " ), concat( " ", "image", " " ))] | //img').re(r':(\d+)')
scrolls = response.xpath('//*[contains(concat( " ", @class, " " ), concat( " ", "image", " " ))] | //strong+//a//img/@title').re(r'\bScroll\b')
for price, hp, scrolls in zip(name, hp, scrolls):
yield {'name': name.strip(), 'hp': hp.strip(), 'scroll':scrolls.strip()}
--- работает без проекта и сохраняет в output.csv
---
from scrapy.crawler import CrawlerRunner
def _run_crawler(spider_cls, settings):
"""
spider_cls: Scrapy Spider class
returns: Twisted Deferred
"""
runner = CrawlerRunner(settings)
return runner.crawl(spider_cls) # return Deferred
def test_scrapy_crawler():
deferred = _run_crawler(MySpider, settings)
@deferred.addCallback
def _success(results):
"""
After crawler completes, this function will execute.
Do your assertions in this function.
"""
@deferred.addErrback
def _error(failure):
raise failure.value
return deferred