I am trying to scrape information from this website example website
I need to get the version 2021 and search by code. Here is my code:
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
from selenium.common.exceptions import NoSuchElementException, StaleElementReferenceException
from selenium.webdriver.support.ui import WebDriverWait, Select
from selenium.webdriver.support import expected_conditions
ignored_exceptions=(NoSuchElementException,StaleElementReferenceException)
options = Options()
options.add_argument('--disable-extensions')
options.add_argument('--headless')
options.add_argument('--no-sandbox')
options.add_argument('--disable-dev-shm-usage')
options.add_argument('--remote-debugging-port=9515')
options.add_argument('--disable-setuid-sandbox')
options.add_argument("--start-maximized")
driver = webdriver.Chrome(service=Service("/usr/bin/chromedriver"), options=options)
url = "https://noc.esdc.gc.ca/"
driver.get(url)
search_by_code = WebDriverWait(driver, 10, ignored_exceptions=ignored_exceptions)\
.until(expected_conditions.presence_of_element_located((By.XPATH, "/html/body/main/div[2]/div/div/div/div/div/div/div/div/ul/li[2]/a")))
# click to activate this option
search_by_code.click()
text_area = WebDriverWait(driver, 10, ignored_exceptions=ignored_exceptions)\
.until(expected_conditions.presence_of_element_located((By.XPATH, "/html/body/main/div[2]/div/div/div/div/div/div/div/div/div/details[2]/div/div/form/div/div[2]/div/input")))
version = Select(WebDriverWait(driver, 10, ignored_exceptions=ignored_exceptions)\
.until(expected_conditions.presence_of_element_located((By.XPATH, "/html/body/main/div[2]/div/div/div/div/div/div/div/div/div/details[2]/div/div/form/div/div[1]/select"))))
search_button = driver.find_element(By.XPATH, '/html/body/main/div[2]/div/div/div/div/div/div/div/div/div/details[2]/div/div/form/div/div[2]/div/div/button')
# select version 2021
version.select_by_value('2021.0')
# click on text area
text_area.click()
# type the text
text_area.send_keys("10010 – Financial managers")
# click the button
search_button.click()
print(source = driver.current_url)
I am not sure what I have missed? I added some comments to describe the logic.
You can use the python-requests
library for this website. I have done a little script below to send requests and get the data. You can send your query to SearchCriteria.CodeSearch
value. You can use BS4
, LXML
, or Scrapy Selector class
and target the values by XPATH
or a CSS selector
.
import re
import requests
cookies = {
'ASP.NET_SessionId': 'u4qffsgfreddkgvdphaxo3pc',
'BIGipServernoc_esdc_gc_ca_http_443.app~noc_esdc_gc_ca_http_443_pool': '639114412.20480.0000',
'gpv_pthl': 'blank%20theme',
'gpv_pc': 'Employment%20and%20Social%20Development%20Canada',
'gpv_pqs': 'blank%20query%20string',
'gpv_pu': 'noc.esdc.gc.ca%2FSearch%2FQuickSearchJobTitleResults',
'gpv_pt': 'Search%20by%20job%20title%20-%20Results%20-%20Canada.ca',
's_plt': '9.44',
's_tp': '1206',
'gpv_url': 'noc.esdc.gc.ca%2FSearch%2FQuickSearchJobTitleResults',
's_ips': '741',
}
headers = {
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
'Accept-Language': 'en-PK,en;q=0.9,ur-PK;q=0.8,ur;q=0.7,en-GB;q=0.6,en-US;q=0.5,sv;q=0.4,it;q=0.3',
'Cache-Control': 'no-cache',
'Connection': 'keep-alive',
# Requests sorts cookies= alphabetically
# 'Cookie': 'ASP.NET_SessionId=u4qffsgfreddkgvdphaxo3pc; BIGipServernoc_esdc_gc_ca_http_443.app~noc_esdc_gc_ca_http_443_pool=639114412.20480.0000; gpv_pthl=blank%20theme; gpv_pc=Employment%20and%20Social%20Development%20Canada; gpv_pqs=blank%20query%20string; gpv_pu=noc.esdc.gc.ca%2FSearch%2FQuickSearchJobTitleResults; gpv_pt=Search%20by%20job%20title%20-%20Results%20-%20Canada.ca; s_plt=9.44; s_tp=1206; gpv_url=noc.esdc.gc.ca%2FSearch%2FQuickSearchJobTitleResults; s_ips=741',
'Origin': 'https://noc.esdc.gc.ca',
'Pragma': 'no-cache',
'Referer': 'https://noc.esdc.gc.ca/Search/QuickSearchJobTitleResults',
'Sec-Fetch-Dest': 'document',
'Sec-Fetch-Mode': 'navigate',
'Sec-Fetch-Site': 'same-origin',
'Sec-Fetch-User': '?1',
'Upgrade-Insecure-Requests': '1',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.0.0 Safari/537.36',
'sec-ch-ua': '".Not/A)Brand";v="99", "Google Chrome";v="103", "Chromium";v="103"',
'sec-ch-ua-mobile': '?0',
'sec-ch-ua-platform': '"Windows"',
}
data = {
'SearchCriteria.CodeVersion': '2021.0',
'SearchCriteria.CodeSearch': '10010 – Financial managers',
'btn-submitSearchNOC': 'Search',
}
r = requests.post('https://noc.esdc.gc.ca/Search/QuickSearchJobTitleResults', cookies=cookies, headers=headers, data=data)
id_ = re.findall(r'objectid=(.*?)&', r.text)[0]
url = f'https://noc.esdc.gc.ca/Structure/NocProfile?objectid={id_}'
r = requests.get(url=url, headers=headers)
print(r.text)
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.