How can I send Dynamic website content to scrapy with the html content generated by selenium browser?

user_14689289 0
Viewed 620

I am working on certain stock-related projects where I have had a task to scrape all data on a daily basis for the last 5 years. i.e from 2016 to date. I particularly thought of using selenium because I can use crawler and bot to scrape the data based on the date. So I used the use of button click with selenium and now I want the same data that is displayed by the selenium browser to be fed by scrappy. This is the website I am working on right now. I have written the following code inside scrappy spider.

class FloorSheetSpider(scrapy.Spider):
    name = "nepse"

    def start_requests(self):

        driver = webdriver.Firefox(executable_path=GeckoDriverManager().install())
        
     
        floorsheet_dates = ['01/03/2016','01/04/2016', up to till date '01/10/2022']

        for date in floorsheet_dates:
            driver.get(
                "https://merolagani.com/Floorsheet.aspx")

            driver.find_element(By.XPATH, "//input[@name='ctl00$ContentPlaceHolder1$txtFloorsheetDateFilter']"
                                ).send_keys(date)
            driver.find_element(By.XPATH, "(//a[@title='Search'])[3]").click()
            total_length = driver.find_element(By.XPATH,
                                               "//span[@id='ctl00_ContentPlaceHolder1_PagerControl2_litRecords']").text
            z = int((total_length.split()[-1]).replace(']', ''))    
            for data in range(z, z + 1):
                driver.find_element(By.XPATH, "(//a[@title='Page {}'])[2]".format(data)).click()
                self.url = driver.page_source
                yield Request(url=self.url, callback=self.parse)

               
    def parse(self, response, **kwargs):
        for value in response.xpath('//tbody/tr'):
            print(value.css('td::text').extract()[1])
            print("ok"*200)

Update: Error after answer is

2022-01-14 14:11:36 [twisted] CRITICAL: 
Traceback (most recent call last):
  File "/home/navaraj/PycharmProjects/first_scrapy/env/lib/python3.8/site-packages/twisted/internet/defer.py", line 1661, in _inlineCallbacks
    result = current_context.run(gen.send, result)
  File "/home/navaraj/PycharmProjects/first_scrapy/env/lib/python3.8/site-packages/scrapy/crawler.py", line 88, in crawl
    start_requests = iter(self.spider.start_requests())
TypeError: 'NoneType' object is not iterable

I want to send current web html content to scrapy feeder but I am getting unusal error for past 2 days any help or suggestions will be very much appreciated.

selenium-webdriver scrapy selenium python
1 Answers

The 2 solutions are not very different. Solution #2 fits better to your question, but choose whatever you prefer.

Solution 1 - create a response with the html's body from the driver and scraping it right away (you can also pass it as an argument to a function):

import scrapy
from selenium import webdriver
from selenium.webdriver.common.by import By
from scrapy.http import HtmlResponse


class FloorSheetSpider(scrapy.Spider):
    name = "nepse"

    def start_requests(self):

        # driver = webdriver.Firefox(executable_path=GeckoDriverManager().install())
        driver = webdriver.Chrome()

        floorsheet_dates = ['01/03/2016','01/04/2016']#, up to till date '01/10/2022']

        for date in floorsheet_dates:
            driver.get(
                "https://merolagani.com/Floorsheet.aspx")

            driver.find_element(By.XPATH, "//input[@name='ctl00$ContentPlaceHolder1$txtFloorsheetDateFilter']"
                                ).send_keys(date)
            driver.find_element(By.XPATH, "(//a[@title='Search'])[3]").click()
            total_length = driver.find_element(By.XPATH,
                                               "//span[@id='ctl00_ContentPlaceHolder1_PagerControl2_litRecords']").text
            z = int((total_length.split()[-1]).replace(']', ''))
            for data in range(1, z + 1):
                driver.find_element(By.XPATH, "(//a[@title='Page {}'])[2]".format(data)).click()
                self.body = driver.page_source

                response = HtmlResponse(url=driver.current_url, body=self.body, encoding='utf-8')
                for value in response.xpath('//tbody/tr'):
                    print(value.css('td::text').extract()[1])
                    print("ok"*200)

        # return an empty requests list
        return []

Solution 2 - with super simple downloader middleware:

(You might have a delay here in parse method so be patient).

import scrapy
from scrapy import Request
from scrapy.http import HtmlResponse
from selenium import webdriver
from selenium.webdriver.common.by import By


class SeleniumMiddleware(object):
    def process_request(self, request, spider):
        url = spider.driver.current_url
        body = spider.driver.page_source
        return HtmlResponse(url=url, body=body, encoding='utf-8', request=request)


class FloorSheetSpider(scrapy.Spider):
    name = "nepse"

    custom_settings = {
        'DOWNLOADER_MIDDLEWARES': {
            'tempbuffer.spiders.yetanotherspider.SeleniumMiddleware': 543,
            # 'projects_name.path.to.your.pipeline': 543
        }
    }
    driver = webdriver.Chrome()

    def start_requests(self):

        # driver = webdriver.Firefox(executable_path=GeckoDriverManager().install())


        floorsheet_dates = ['01/03/2016','01/04/2016']#, up to till date '01/10/2022']

        for date in floorsheet_dates:
            self.driver.get(
                "https://merolagani.com/Floorsheet.aspx")

            self.driver.find_element(By.XPATH, "//input[@name='ctl00$ContentPlaceHolder1$txtFloorsheetDateFilter']"
                                ).send_keys(date)
            self.driver.find_element(By.XPATH, "(//a[@title='Search'])[3]").click()
            total_length = self.driver.find_element(By.XPATH,
                                               "//span[@id='ctl00_ContentPlaceHolder1_PagerControl2_litRecords']").text
            z = int((total_length.split()[-1]).replace(']', ''))
            for data in range(1, z + 1):
                self.driver.find_element(By.XPATH, "(//a[@title='Page {}'])[2]".format(data)).click()
                self.body = self.driver.page_source
                self.url = self.driver.current_url

                yield Request(url=self.url, callback=self.parse, dont_filter=True)

    def parse(self, response, **kwargs):
        print('test ok')
        for value in response.xpath('//tbody/tr'):
            print(value.css('td::text').extract()[1])
            print("ok"*200)

Notice that I've used chrome so change it back to firefox like in your original code.

user_164297800
Related