Develop Reference

How to scrape multiple pages from search results all at once

I am trying to scrape multiple pages from search results and print it all at once, but got an empty list instead.
Here is the code I used:
from selenium import webdriver
from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver.common.by import By
element_list = []
for skip in range(0, 20, 10):
page_url = "https://jdih.esdm.go.id/index.php/web/result?tahun_terbit=2022,2021,2020,2019,2018,2017,2016,2015,2014&skip=" + str(skip)
driver = webdriver.Chrome(ChromeDriverManager().install())
driver.get(page_url)
Tahun = driver.find_elements(By.CSS_SELECTOR, 'div.numb separator')
No_Peraturan = driver.find_elements(By.CSS_SELECTOR, 'span.result-value')
Nama_Peraturan = driver.find_elements(By.CSS_SELECTOR, 'div.result__content__item__title')
Deskripsi = driver.find_elements(By.CSS_SELECTOR, 'div.result__content__item__desc')
for i in range(len(Tahun)):
element_list.append([Tahun[i].text, No_Peraturan[i].text, Nama_Peraturan[i].text, Deskripsi[i].text])
print(element_list)
driver.close()
The code return only return an empty list like in this picture
enter image description here
Note: the website does not use 'page' as generally use for search results, but uses 'skip' instead
Anyone can help me with this ?

The CSS selector to find Tahun elements is incorrect as there are 2 classes assigned to the div. This results in Tahun being an empty list and since the loop to append text to element_list is based on the length of Tahun, nothing gets appended.
Update the selector to below.
Tahun = driver.find_elements(By.CSS_SELECTOR, 'div.numb.separator')

Selenium webdriver loops through all pages, but only scraping data for first page

I am attempting to scrape data through multiple pages (36) from a website to gather the document number and the revision number for each available document and save it to two different lists. If I run the code block below for each individual page, it works perfectly. However, when I added the while loop to loop through all 36 pages, it will loop, but only the data from the first page is saved.
#sam.gov website
url = 'https://sam.gov/search/?index=sca&page=1&sort=-modifiedDate&pageSize=25&sfm%5Bstatus%5D%5Bis_active%5D=true&sfm%5BwdPreviouslyPerformedWrapper%5D%5BpreviouslyPeformed%5D=prevPerfNo%2F'
#webdriver
driver = webdriver.Chrome(options = options_, executable_path = r'C:/Users/439528/Python Scripts/Spyder/chromedriver.exe' )
driver.get(url)
#get rid of pop up window
WebDriverWait(driver, 10).until(EC.element_to_be_clickable((By.CSS_SELECTOR, '#sds-dialog-0 > button > usa-icon > i-bs > svg'))).click()
#list of revision numbers
revision_num = []
#empty list for all the WD links
WD_num = []
substring = '2015'
current_page = 0
while True:
current_page += 1
if current_page == 36:
#find all elements on page named "field name". For each one, get the text. if the text is 'Revision Date'
#then, get the 'sibling' element, which is the actual revision number. append the date text to the revision_num list.
elements = driver.find_elements_by_class_name('sds-field__name')
wd_links = driver.find_elements_by_class_name('usa-link')
for i in elements:
element = i.text
if element == 'Revision Number':
revision_numbers = i.find_elements_by_xpath("./following-sibling::div")
for x in revision_numbers:
a = x.text
revision_num.append(a)
#finding all links that have the partial text 2015 and putting the wd text into the WD_num list
for link in wd_links:
wd = link.text
if substring in wd:
WD_num.append(wd)
print('Last Page Complete!')
break
else:
#find all elements on page named "field name". For each one, get the text. if the text is 'Revision Date'
#then, get the 'sibling' element, which is the actual revision number. append the date text to the revision_num list.
elements = driver.find_elements_by_class_name('sds-field__name')
wd_links = driver.find_elements_by_class_name('usa-link')
for i in elements:
element = i.text
if element == 'Revision Number':
revision_numbers = i.find_elements_by_xpath("./following-sibling::div")
for x in revision_numbers:
a = x.text
revision_num.append(a)
#finding all links that have the partial text 2015 and putting the wd text into the WD_num list
for link in wd_links:
wd = link.text
if substring in wd:
WD_num.append(wd)
#click on next page
click_icon = WebDriverWait(driver, 5, 0.25).until(EC.visibility_of_element_located([By.ID,'bottomPagination-nextPage']))
click_icon.click()
WebDriverWait(driver, 5).until(EC.presence_of_element_located((By.ID, 'main-container')))
Things I've tried:
I added the WebDriverWait in order to slow the script down for the page to load and/or elements to be clickable/located
I declared the empty lists outside the loop so it does not overwrite over each iteration
I have edited the while loop multiple times to either count up to 36 (while current_page <37) or moved the counter to the top or bottom of the loop)
Any ideas? TIA.
EDIT: added screenshot of 'field name'

I have refactor your code and made things very simple.
driver = webdriver.Chrome(options = options_, executable_path = r'C:/Users/439528/Python Scripts/Spyder/chromedriver.exe' )
revision_num = []
WD_num = []
for page in range(1,37):
url = 'https://sam.gov/search/?index=sca&page={}&sort=-modifiedDate&pageSize=25&sfm%5Bstatus%5D%5Bis_active%5D=true&sfm%5BwdPreviouslyPerformedWrapper%5D%5BpreviouslyPeformed%5D=prevPerfNo%2F'.format(page)
driver.get(url)
if page==1:
WebDriverWait(driver, 10).until(EC.element_to_be_clickable((By.CSS_SELECTOR, '#sds-dialog-0 > button > usa-icon > i-bs > svg'))).click()
elements = WebDriverWait(driver, 10).until(EC.visibility_of_all_elements_located((By.XPATH,"//a[contains(#class,'usa-link') and contains(.,'2015')]")))
wd_links = WebDriverWait(driver, 10).until(EC.visibility_of_all_elements_located((By.XPATH,"//div[#class='sds-field__name' and text()='Revision Number']/following-sibling::div")))
for element in elements:
revision_num.append(element.text)
for wd_link in wd_links:
WD_num.append(wd_link.text)
print(revision_num)
print(WD_num)
if you know only 36 pages to iterate you can pass the value in the url.
wait for element visible using webdriverwait
construct your xpath in such a way so can identify element uniquely without if, but.
console output on my terminal:

How to to iterate over hrefs with selenium?

I've been trying to get all the hrefs of a news article home page. In the end, I want to create something that gives me the n-most used words from all the news articles. To do that, I figured I needed the hrefs first to then click on them one after another.
With a lot of help from another user of this platform, this is the code I've got right now:
from bs4 import BeautifulSoup
from selenium import webdriver
url = 'https://ad.nl'
# launch firefox with your url above
# note that you could change this to some other webdriver (e.g. Chrome)
driver = webdriver.Chrome()
driver.get(url)
# click the "accept cookies" button
btn = driver.find_element_by_name('action')
btn.click()
# grab the html. It'll wait here until the page is finished loading
html = driver.page_source
# parse the html soup
soup = BeautifulSoup(html.lower(), "html.parser")
articles = soup.findAll("article")
for i in articles:
article = driver.find_element_by_class_name('ankeiler')
hrefs = article.find_element_by_css_selector('a').get_attribute('href')
print(hrefs)
driver.quit()
It gives me the first href I think, but it won't iterate over the next ones. It just gives me the first href as many times as it has to iterate. Does anyone know how I make it go to the next href instead of being stuck on the first one?
PS. if anyone has some suggestions on how to further do my little project, feel free to share them as I have a lot of things yet to learn about Python and programming in general.

Instead of using beautiful soup, how about this?
articles = driver.find_elements_by_css_selector('article')
for i in articles:
href = i.find_element_by_css_selector('a').get_attribute('href')
print(href)

To improve on my previous answer, I have written a full solution to your problem:
from selenium import webdriver
url = 'https://ad.nl'
#Set up selenium driver
driver = webdriver.Chrome()
driver.get(url)
#Click the accept cookies button
btn = driver.find_element_by_name('action')
btn.click()
#Get the links of all articles
article_elements = driver.find_elements_by_xpath('//a[#class="ankeiler__link"]')
links = [link.get_attribute('href') for link in article_elements]
#Create a dictionary for every word in the articles
words = dict()
#Iterate through every article
for link in links:
#Get the article
driver.get(link)
#get the elements that are the body of the article
article_elements = driver.find_elements_by_xpath('//*[#class="article__paragraph"]')
#Initalise a empty string
article_text = ''
#Add all the text from the elements to the one string
for element in article_elements:
article_text+= element.text + " "
#Convert all character to lower case
article_text = article_text.lower()
#Remove all punctuation other than spaces
for char in article_text:
if ord(char) > 122 or ord(char) < 97:
if ord(char) != 32:
article_text = article_text.replace(char,"")
#Split the article into words
for word in article_text.split(" "):
#If the word is already in the article update the count
if word in words:
words[word] += 1
#Otherwise make a new entry
else:
words[word] = 1
#Print the final dictionary (Very large so maybe sort for most occurring words and display top 10)
#print(words)
#Sort words by most used
most_used = sorted(words.items(), key=lambda x: x[1],reverse=True)
#Print top 10 used words
print("TOP 10 MOST USED: ")
for i in range(10):
print(most_used[i])
driver.quit()
Works fine for me, let me know if you get any errors.

To get all hrefs in an article you can do:
hrefs = article.find_elements_by_xpath('//a')
#OR article.find_element_by_css_selector('a')
for href in hrefs:
print(href.get_attribute('href'))
To progress with the project though, maybe the bellow would help:
hrefs = article.find_elements_by_xpath('//a')
links = [href.get_attribute("href") for href in hrefs]
for link in link:
driver.get(link)
#Add all words in the article to a dictionary with the key being the words and
#the value being the number of times they occur

How can i scrape information from web page?

I am new to programming and need some help with my web-crawler.
At the moment, I have my code opening up every web-page in the list. However, I wish to extract information from each one it loads. This is what I have.
from selenium import webdriver
import csv
driver = webdriver.Firefox()
links_code = driver.find_elements_by_xpath('//a[#class="in-match"]')
first_two = links_code[0:2]
first_two_links = []
for i in first_two:
link = i.get_attribute("href")
first_two_links.append(link)
for i in first_two_links:
driver.get(i)
This loops through the first two pages but scrapes no info. So I tried adding to the for-loop as follows
odds = []
for i in first_two_links:
driver.get(i)
driver.find_element_by_xpath('//span[#class="table-main__detail-
odds--hasarchive"]')
odds.append(odd)
However. This runs into an error.
Any help much appreciated.

You are not actually appending anything! you need to assign a variable to
driver.find_element_by_xpath('//span[#class="table-main__detail-
odds--hasarchive"]')
then append it to the list!
from selenium import webdriver;
import csv;
driver = webdriver.Firefox();
links_code : list = driver.find_elements_by_xpath('//a[#class="in-match"]');
first_two : list = links_code[0:2];
first_two_links : list = [];
i : int;
for i in first_two:
link = i.get_attribute("href");
first_two_links.append(link);
for i in first_two_links:
driver.get(i);
odds : list = [];
i :int;
for i in first_two_links:
driver.get(i);
o = driver.find_element_by_xpath('//span[#class="table-main__detail- odds--hasarchive"]');
odds.append(o);

First, after you start the driver you need to go to a website...
Second, in the second for loop, you are trying to append the wrong object... use i not odd or make odd = driver.find_element_by_xpath('//span[#class="table-main__detail-odds--hasarchive"]')
If you can provide the URL or the HTML we can help more!
Try this (I have used Google as an example you will need to change the code...):
from selenium import webdriver
driver = webdriver.Firefox()
driver.get("https://www.google.com")
links_code = driver.find_elements_by_xpath('//a')
first_two = links_code[0:2]
first_two_links = []
for i in first_two:
link = i.get_attribute("href")
first_two_links.append(link)
print(link)
odds = []
for i in first_two_links:
driver.get(i)
odd = driver.page_source
print(odd)
# driver.find_element_by_xpath('//span[#class="table-main__detail- odds--hasarchive"]')
odds.append(odd)

StaleElementReferenceException selenium webdriver python

I'm writing a crawler using Selenium, Python and PhantomJS to use Google's reverse image search. So far I've successfully been able to upload an image and crawl the search results on the first page. However, when I try to click on the search results navigation, I'm getting a StaleElementReferenceError. I have read about it in many posts but still I could not implement the solution. Here is the code that breaks:
ele7 = browser.find_element_by_id("nav")
ele5 = ele7.find_elements_by_class_name("fl")
count = 0
for elem in ele5:
if count <= 2:
print str(elem.get_attribute("href"))
elem.click()
browser.implicitly_wait(20)
ele6 = browser.find_elements_by_class_name("rc")
for result in ele6:
f = result.find_elements_by_class_name("r")
for line in f:
link = line.find_elements_by_tag_name("a")[0].get_attribute("href")
links.append(link)
parsed_uri = urlparse(link)
domains.append('{uri.scheme}://{uri.netloc}/'.format(uri=parsed_uri))
count += 1
The code breaks at print str(elem.get_attribute("href")) . How can I solve this?
Thanks in advance.

Clicking a link will cause the browser to go to another page; make references to the elements in old page (ele5, elem) invalid.
Modify the code not to reference invalid elements.
For example, you can get urls before you visit other pages:
ele7 = browser.find_element_by_id("nav")
ele5 = ele7.find_elements_by_class_name("fl")
urls = [elem.get_attribute('href') for elem in ele5] # <-----
browser.implicitly_wait(20)
for url in urls[:2]: # <------
print url
browser.get(url) # <------ used `browser.get` instead of `click`.
# ; using `element.click` will cause the error.
ele6 = browser.find_elements_by_class_name("rc")
for result in ele6:
f = result.find_elements_by_class_name("r")
for line in f:
link = line.find_elements_by_tag_name("a")[0].get_attribute("href")
links.append(link)
parsed_uri = urlparse(link)
domains.append('{uri.scheme}://{uri.netloc}/'.format(uri=parsed_uri))