Created
October 29, 2019 17:45
-
-
Save rafikahmed/c9f0e6b813a15ad09870d80bd79cd016 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding: utf-8 -*- | |
import scrapy | |
import json | |
class FreelancerComRuSpider(scrapy.Spider): | |
name = 'freelancer_com_ru' | |
allowed_domains = ['www.freelancer.com.ru'] | |
iDisplayStart = 0 | |
def start_requests(self): | |
yield scrapy.Request( | |
url=f'https://www.freelancer.com.ru/ajax/table/project_contest_datatable.php?tag=&type=false&budget_min=false&budget_max=false&contest_budget_min=false&contest_budget_max=false&hourlyrate_min=false&hourlyrate_max=false&hourlyProjectDuration=2&skills_chosen=57&languages=en%2Cru&status=open&vicinity=false&countries=false&lat=false&lon=false&iDisplayStart={self.iDisplayStart}&iDisplayLength=50&iSortingCols=1&iSortCol_0=9&sSortDir_0=desc&format_version=3&', | |
callback=self.parse | |
) | |
def parse(self, response): | |
json_response = json.loads(response.body) | |
projects = json_response.get('aaData') | |
for project in projects: | |
yield { | |
'project_name': project.get('project_name'), | |
'seo_url': project.get('seo_url'), | |
'description': project.get('project_desc'), | |
'bid_average': project.get('bid_avg'), | |
'bid_count': project.get('bid_count'), | |
'project_id': project.get('project_id'), | |
'min_budget': project.get('minbudget'), | |
'max_budget': project.get('maxbudget') | |
} | |
if self.iDisplayStart <= 1850: | |
self.iDisplayStart += 50 | |
yield scrapy.Request( | |
url=f'https://www.freelancer.com.ru/ajax/table/project_contest_datatable.php?tag=&type=false&budget_min=false&budget_max=false&contest_budget_min=false&contest_budget_max=false&hourlyrate_min=false&hourlyrate_max=false&hourlyProjectDuration=2&skills_chosen=57&languages=en%2Cru&status=open&vicinity=false&countries=false&lat=false&lon=false&iDisplayStart={self.iDisplayStart}&iDisplayLength=50&iSortingCols=1&iSortCol_0=9&sSortDir_0=desc&format_version=3&', | |
callback=self.parse | |
) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment