When I try to scrape a certain web site (with both, spider and shell), I get the following error:
twisted.web._newclient.ResponseNeverReceived: [
Here is 100% working code.
What you need to do is you have to send request headers as well.
Also set ROBOTSTXT_OBEY = False
in settings.py
# -*- coding: utf-8 -*-
import scrapy, logging
from scrapy.http.request import Request
class Test1SpiderSpider(scrapy.Spider):
name = "test1_spider"
def start_requests(self):
headers = {
"Host": "www.firmenabc.at",
"Connection": "keep-alive",
"Cache-Control": "max-age=0",
"Upgrade-Insecure-Requests": "1",
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
"DNT": "1",
"Accept-Encoding": "gzip, deflate, sdch",
"Accept-Language":"en-US,en;q=0.8"
}
yield Request(url= 'http://www.firmenabc.at/result.aspx?what=&where=Graz', callback=self.parse_detail_page, headers=headers)
def parse_detail_page(self, response):
logging.info(response.body)
EDIT:
You can see what headers to send by inspecting the URLs in Dev Tools