Empty List For Hrefs To Achieve Pagination Through JavaScript Onclick Functions

My intension is to achieve the pagination from javascript functions, so for example I am taking the URL as http://events.justdial.com/events/index.php?city=Hyderabad, from this URL

Solution 1:

If you tracked the requests, you'll find post requests to the following URL : http://events.justdial.com/events/search.php

Post Data :

city:Hyderabad 
cat:0 
area:0 
fromDate: 
toDate: 
subCat:0 
pageNo:2
fetch:events

and the response is in JSON format.

So, your code should be the following

import re
import json

class justdialdotcomSpider(BaseSpider):
    name = "justdialdotcom"
    domain_name = "www.justdial.com"
    start_urls = ["http://events.justdial.com/events/search.php"]


    # Initial request
    def parse(self, response):
        return [FormRequest(url="http://events.justdial.com/events/search.php",
                                        formdata={'fetch': 'area',
                                                  'pageNo': '1',
                                                  'city' : 'Hyderabad',
                                                  'cat' : '0',
                                                  'area' : '0',
                                                  'fromDate': '',
                                                  'toDate' : '',
                                                  'subCat' : '0'
                                                  },
                                        callback=self.area_count
                                        )]


# Get total count and paginate through events
    def area_count(self, response):
        total_count = 0
        for area in  json.loads(response.body):
            total_count += int(area["count"])

        pages_count = (total_count / 10) + 1

        page = 1
        while (page <= pages_count):
            yield FormRequest(url="http://events.justdial.com/events/search.php",
                                        formdata={'fetch': 'events',
                                                  'pageNo': str(page),
                                                  'city' : 'Hyderabad',
                                                  'cat' : '0',
                                                  'area' : '0',
                                                  'fromDate': '',
                                                  'toDate' : '',
                                                  'subCat' : '0'
                                                  },
                                        callback=self.parse_events
                                        )
            page += 1


# parse events 
    def parse_events(self, response):
        events = json.loads(response.body)
        events.pop(0)

        for event_details in events:
            yield FormRequest(url="http://events.justdial.com/events/search.php",
                                        formdata={'fetch': 'event',
                                                  'eventId': str(event_details["id"]),
                                                  },
                                        callback=self.parse_event
                                        )



    def parse_event(self, response):
        event_details = json.loads(response.body)
        items = []
        #item = Product()

        items.append(item)
        return items