'Scrapy: 403 TTP status code is not handled or not allowed
I have followed a few websites to add the headers on my request to get the results, but it is not working at all. This is my code: I have no idea how this should work.. someone help me plz
class JobsSpider(scrapy.Spider):
name = "ziprecruiter"
#user_agent = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1"
#start_urls = [f'https://www.ziprecruiter.com/jobs-search?search=Port&location=Vancouver,%20CA']
#user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36'
#allowed_domains = ["ziprecruiter.com"]
#start_urls = ['https://www.ziprecruiter.com/']
def __init__(self, job='Porter',location='Vancouver,%20',country="CA", **kwargs):
self.name="ziprecruiter"
self.allowed_domains = ["ziprecruiter.com"]
self.combine = location+country
self.user_agent = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1"
self.job = job
self.start_urls = ['https://www.ziprecruiter.com/']
#self.header={'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:48.0) Gecko/20100101 Firefox/48.0'}
#self.user_agent = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1"
#self.start_urls = [f'https://www.ziprecruiter.com/jobs-search?search={category}&location={self.combine}'] # py36
super().__init__(**kwargs) # python3
#.xpath('//div[@class="job_title_raw"]').extract()/a[@class="job_link"]/h2[@class="title"]
def parse(self, response):
response.request.headers.get("referer")
request = scrapy.FormRequest.from_response(
response,
formname='search_form job_search_form',
formdata={'search':'Porter','location':''},
)
print(request.body)
yield request```
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|