CODEWITHSUNDEEP
pythonpython-3.xseleniumweb-scrapingscrapy
SIM
SIM

Reputation: 22440

Trouble running a parser created using scrapy with selenium

I've written a scraper in Python scrapy in combination with selenium to scrape some titles from a website. The css selectors defined within my scraper is flawless. I wish my scraper to keep on clicking on the next page and parse the information embedded in each page. It is doing fine for the first page but when it comes to play the role for selenium part the scraper keeps clicking on the same link over and over again.

As this is my first time to work with selenium along with scrapy, I don't have any idea to move on successfully. Any fix will be highly appreciated.

If I try like this then it works smoothly (there is nothing wrong with selectors):

class IncomeTaxSpider(scrapy.Spider):
    name = "taxspider"

    start_urls = [
        'https://www.incometaxindia.gov.in/Pages/utilities/exempted-institutions.aspx',
    ]

    def __init__(self):
        self.driver = webdriver.Chrome()
        self.wait = WebDriverWait(self.driver, 10)

    def parse(self,response):
        self.driver.get(response.url)

        while True:
            for elem in self.wait.until(EC.presence_of_all_elements_located((By.CSS_SELECTOR,"h1.faqsno-heading"))):
                name = elem.find_element_by_css_selector("div[id^='arrowex']").text
                print(name)

            try:
                self.wait.until(EC.visibility_of_element_located((By.CSS_SELECTOR, "input[id$='_imgbtnNext']"))).click()
                self.wait.until(EC.staleness_of(elem))
            except TimeoutException:break

But my intention is to make my script run this way:

import scrapy
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException

class IncomeTaxSpider(scrapy.Spider):
    name = "taxspider"

    start_urls = [
        'https://www.incometaxindia.gov.in/Pages/utilities/exempted-institutions.aspx',
    ]

    def __init__(self):
        self.driver = webdriver.Chrome()
        self.wait = WebDriverWait(self.driver, 10)

    def click_nextpage(self,link):
        self.driver.get(link)
        elem = self.wait.until(EC.visibility_of_element_located((By.CSS_SELECTOR, "div[id^='arrowex']")))

        #It keeeps clicking on the same link over and over again

        self.wait.until(EC.visibility_of_element_located((By.CSS_SELECTOR, "input[id$='_imgbtnNext']"))).click()  
        self.wait.until(EC.staleness_of(elem))


    def parse(self,response):
        while True:
            for item in response.css("h1.faqsno-heading"):
                name = item.css("div[id^='arrowex']::text").extract_first()
                yield {"Name": name}

            try:
                self.click_nextpage(response.url) #initiate the method to do the clicking
            except TimeoutException:break

These are the titles visible on that landing page (to let you know what I'm after):

INDIA INCLUSION FOUNDATION
INDIAN WILDLIFE CONSERVATION TRUST
VATSALYA URBAN AND RURAL DEVELOPMENT TRUST

I'm not willing to get the data from that site, so any alternative approach other than what I've tried above is useless to me. My only intention is to have any solution related to the way I tried in my second approach.

Upvotes: 2

Views: 623

Answers (5)

Tarun Lalwani
Tarun Lalwani

Reputation: 146520

Your initial code was almost correct with one key piece missing from it. You were using the same response object always. The response object needs to be from the latest page source.

Also you were browsing the link again and again in click next page which was resetting it to page 1 every time. That is why you get page 1 and 2 (max). You need to get the url only once in the parse stage and then let the next page click to happen

Below is final code working fine

class IncomeTaxSpider(scrapy.Spider):
    name = "taxspider"

    start_urls = [
        'https://www.incometaxindia.gov.in/Pages/utilities/exempted-institutions.aspx',
    ]

    def __init__(self):
        self.driver = webdriver.Chrome()
        self.wait = WebDriverWait(self.driver, 10)

    def click_nextpage(self,link):
        # self.driver.get(link)
        elem = self.wait.until(EC.visibility_of_element_located((By.CSS_SELECTOR, "div[id^='arrowex']")))

        #It keeeps clicking on the same link over and over again

        self.wait.until(EC.visibility_of_element_located((By.CSS_SELECTOR, "input[id$='_imgbtnNext']"))).click()
        self.wait.until(EC.staleness_of(elem))


    def parse(self, response):
        self.driver.get(response.url)

        while True:
            for item in response.css("h1.faqsno-heading"):
                name = item.css("div[id^='arrowex']::text").extract_first()
                yield {"Name": name}

            try:
                self.click_nextpage(response.url) #initiate the method to do the clicking
                response = response.replace(body=self.driver.page_source)
            except TimeoutException:break

After that change it works perfect

Working

Upvotes: 1

Maxwell77
Maxwell77

Reputation: 939

import scrapy
import time
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException
from scrapy.crawler import CrawlerProcess

class IncomeTaxSpider(scrapy.Spider):
    name = "taxspider"

    start_urls = [
        'https://www.incometaxindia.gov.in/Pages/utilities/exempted-institutions.aspx',
    ]

    def __init__(self):
        self.driver = webdriver.Chrome()
        self.wait = WebDriverWait(self.driver, 10)

        link = 'https://www.incometaxindia.gov.in/Pages/utilities/exempted-institutions.aspx'
        self.driver.get(link)

    def click_nextpage(self):        
        elem = self.wait.until(EC.visibility_of_element_located((By.CSS_SELECTOR, "div[id^='arrowex']")))

        #It keeeps clicking on the same link over and over again

        self.wait.until(EC.visibility_of_element_located((By.CSS_SELECTOR, "input[id$='_imgbtnNext']"))).click()  
        self.wait.until(EC.staleness_of(elem))
        time.sleep(4)

    def parse(self,response):
        while True:
            for item in response.css("h1.faqsno-heading"):
                name = item.css("div[id^='arrowex']::text").extract_first()
                yield {"Name": name}

            try:
                self.click_nextpage() #initiate the method to do the clicking
            except TimeoutException:break

process = CrawlerProcess()

process.crawl(IncomeTaxSpider)
process.start()

Upvotes: 1

Sahil Agarwal
Sahil Agarwal

Reputation: 595

Create a self.page_num or something.

def parse(self,response):
    self.pages = self.driver.find_element_by_css_selector("#ctl00_SPWebPartManager1_g_d6877ff2_42a8_4804_8802_6d49230dae8a_ctl00_totalRecordsDiv.act_search_footer span")
    self.pages = int(self.pages.split('of ')[1].split(']')[0])

    self.page_num = 1

    while self.page_num <= self.pages:
        for item in response.css("h1.faqsno-heading"):
            name = item.css("div[id^='arrowex']::text").extract_first()
            yield {"Name": name}

        try:
            self.click_nextpage(response.url) #initiate the method to do the clicking
        except TimeoutException:break

def click_nextpage(self,link):
    self.driver.get(link)
    elem = self.wait.until(EC.visibility_of_element_located((By.CSS_SELECTOR, "div[id^='arrowex']")))

    page_link = 'ctl00_SPWebPartManager1_g_d6877ff2_42a8_4804_8802_6d49230dae8a_ctl00_lnkBtn_' + str(self.page_num)
    self.page_num = self.page_num + 1


    self.wait.until(EC.visibility_of_element_located((By.CSS_SELECTOR, "input[id$='_imgbtnNext']"))).click()  
    self.wait.until(EC.staleness_of(elem))

Upvotes: 0

Krishna
Krishna

Reputation: 198

Whenever the page gets loaded using the 'Next Page' arrow (using Selenium) it gets reset back to Page '1'. Not sure about the reason for this (may be the java script) Hence changed the approach to use the input field to enter the page number needed and hitting ENTER key to navigate.

Here is the modified code. Hope this may be useful for you.

import scrapy
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.keys import Keys

class IncomeTaxSpider(scrapy.Spider):
    name = "taxspider"
    start_urls = [
        'https://www.incometaxindia.gov.in/Pages/utilities/exempted-institutions.aspx',
    ]
    def __init__(self):
        self.driver = webdriver.Firefox()
        self.wait = WebDriverWait(self.driver, 10)

    def click_nextpage(self,link, number):
        self.driver.get(link)
        elem = self.wait.until(EC.visibility_of_element_located((By.CSS_SELECTOR, "div[id^='arrowex']")))

        #It keeeps clicking on the same link over and over again

    inputElement = self.driver.find_element_by_xpath("//input[@id='ctl00_SPWebPartManager1_g_d6877ff2_42a8_4804_8802_6d49230dae8a_ctl00_txtPageNumber']")
    inputElement.clear()
    inputElement.send_keys(number)
    inputElement.send_keys(Keys.ENTER)
        self.wait.until(EC.staleness_of(elem))


    def parse(self,response):
        number = 1
        while number < 10412: #Website shows it has 10411 pages.
            for item in response.css("h1.faqsno-heading"):
                name = item.css("div[id^='arrowex']::text").extract_first()
                yield {"Name": name}
                print (name)

            try:
                number += 1
                self.click_nextpage(response.url, number) #initiate the method to do the clicking
            except TimeoutException:break

Upvotes: 0

Andersson
Andersson

Reputation: 52665

In case you need pure Selenium solution:

driver.get("https://www.incometaxindia.gov.in/Pages/utilities/exempted-institutions.aspx")

while True:
    for item in wait(driver, 10).until(EC.presence_of_all_elements_located((By.CSS_SELECTOR, "div[id^='arrowex']"))):
        print(item.text)
    try:
        driver.find_element_by_xpath("//input[@text='Next' and not(contains(@class, 'disabledImageButton'))]").click()
    except NoSuchElementException:
        break

Upvotes: 1

Related Questions