我试图从json获得数据，但他们给予我错误，HTTP status code is not handled or not allowed有任何解决方案如何处理这些错误在scrappy什么是这些错误会发生的原因是，许多请求发生，为什么他们显示这些错误，这是页面链接https://www.nationalhardwareshow.com/en-us/attend/exhibitor-list.html
import scrapy
from scrapy import FormRequest
from scrapy.crawler import CrawlerProcess
from scrapy.http import Request
class TestSpider(scrapy.Spider):
name = 'test'
url="https://xd0u5m6y4r-dsn.algolia.net/1/indexes/event-edition-eve-e6b1ae25-5b9f-457b-83b3-335667332366_en-us/query"
headers = {
'Accept-Language': 'en-GB,en-US;q=0.9,en;q=0.8,pt;q=0.7',
'Connection': 'keep-alive',
'Origin': 'https://www.nationalhardwareshow.com',
'Referer': 'https://www.nationalhardwareshow.com/',
'Sec-Fetch-Dest': 'empty',
'Sec-Fetch-Mode': 'cors',
'Sec-Fetch-Site': 'cross-site',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.0.0 Safari/537.36',
'accept': 'application/json',
'content-type': 'application/x-www-form-urlencoded',
'sec-ch-ua': '".Not/A)Brand";v="99", "Google Chrome";v="103", "Chromium";v="103"',
'sec-ch-ua-mobile': '?0',
'sec-ch-ua-platform': '"Windows"',
}
params = {
'x-algolia-agent': 'Algolia for vanilla JavaScript 3.27.1',
'x-algolia-application-id': 'XD0U5M6Y4R',
'x-algolia-api-key': 'd5cd7d4ec26134ff4a34d736a7f9ad47',
'params':'query=&page=0&facetFilters=&optionalFilters=%5B%5D',
}
def start_requests(self):
yield scrapy.FormRequest(
url=self.url,
method='POST',
headers=self.headers,
formdata=self.params,
callback=self.parse,
)
def parse(self,response):
print(response.json())
import scrapy
from scrapy import FormRequest
from scrapy.crawler import CrawlerProcess
from scrapy.http import Request
class TestSpider(scrapy.Spider):
name = 'test'
url="https://xd0u5m6y4r-dsn.algolia.net/1/indexes/event-edition-eve-e6b1ae25-5b9f-457b-83b3-335667332366_en-us/query"
headers = {
'Accept-Language': 'en-GB,en-US;q=0.9,en;q=0.8,pt;q=0.7',
'Connection': 'keep-alive',
'Origin': 'https://www.nationalhardwareshow.com',
'Referer': 'https://www.nationalhardwareshow.com/',
'Sec-Fetch-Dest': 'empty',
'Sec-Fetch-Mode': 'cors',
'Sec-Fetch-Site': 'cross-site',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.0.0 Safari/537.36',
'accept': 'application/json',
'content-type': 'application/x-www-form-urlencoded',
'sec-ch-ua': '".Not/A)Brand";v="99", "Google Chrome";v="103", "Chromium";v="103"',
'sec-ch-ua-mobile': '?0',
'sec-ch-ua-platform': '"Windows"',
}
params = {
'x-algolia-agent': 'Algolia for vanilla JavaScript 3.27.1',
'x-algolia-application-id': 'XD0U5M6Y4R',
'x-algolia-api-key': 'd5cd7d4ec26134ff4a34d736a7f9ad47',
'params':'query=&page=0&facetFilters=&optionalFilters=%5B%5D',
}
def start_requests(self):
yield scrapy.FormRequest(
url=self.url,
method='POST',
headers=self.headers,
formdata=self.params,
callback=self.parse,
)
def parse(self,response):
print(response.json())
1条答案
按热度按时间r1zk6ea11#
你得到的是
HTTP status code is not handled or not allowed，因为头文件和参数太多了。输出：