Looping through URL links in CSV file with Python Selenium - python

I've got a collection of URL's in a csv file and I want to loop through these links and open each link in the CSV one at a time. I'm getting several different errors depending on what I try but nonetheless I can't get the browser to open the links. The print shows that the links are there.
When I run my code i get the following error:
Traceback (most recent call last):
File "/Users/Main/PycharmProjects/ScrapingBot/classpassgiit.py", line 26, in <module>
open = browser.get(link_loop)
TypeError: Object of type bytes is not JSON serializable
Can someone help me with my code below if I am missing something or if i am doing it wrong.
My code:
import csv
from selenium import webdriver
from bs4 import BeautifulSoup as soup
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait as browser_wait
from selenium.webdriver.support import expected_conditions as EC
import requests
browser = webdriver.Chrome(executable_path=r'./chromedriver')
contents = []
with open('ClassPasslite.csv', 'rt') as cp_csv:
cp_url = csv.reader(cp_csv)
for row in cp_url:
links = row[0]
contents.append(links)
for link in contents:
url_html = requests.get(links)
for link_loop in url_html:
print(contents)
open = browser.get(link_loop)


Apparently, you are messing something up with the names. Without having a copy of the .csv file, I cannot reproduce the error - hence, I will assume that you correctly extract the link from the text file.
In the second part of your code, you use requests.get to get the links (mind the plural) option, but links apparently is an element that you define in the previous section (links = row[0]), whereas link is the actual object you define in the for loop. Below you can find a version of the code that might be a helpful starting point.
Let me add, though, that the contemporaneous use of requests and selenium in this case makes little sense in your context: why getting an HTML page and then loop over its elements to get other pages with selenium?
import csv
import requests
browser = webdriver.Chrome(executable_path=r'./chromedriver')
contents = []
with open('ClassPasslite.csv', 'rt') as cp_csv:
cp_url = csv.reader(cp_csv)
for row in cp_url:
links = row[0]
contents.append(links)
for link in contents:
url_html = requests.get(link) # now this is singular
# Do what you have to do here with requests, in spite of using selenium #


Since you have not provided any form of what is contained in your variable contents I will assume that it is a list of url strings.
As #cap.py mentioned you are messing up by using requests and selenium at the same time. When you do a GET web request, the server at the destination will send you a text response. This text can be simply some text, like Hello world! or it can be some html. But this html code as to be interpreted in your computer which sent the request.
That's the point of selenium over requests: requests return the text gathered from the destination (url) while selenium ask a browser (e.g. Chrome) to do gather the text and if this text is some html, to interpret it to give you a real readable web page. Moreover the browser is running the javascript inside your page so dynamic pages works as well.
In the end the only thing needed to run your code is to do this:
import csv
from selenium import webdriver
from bs4 import BeautifulSoup as soup
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait as browser_wait
from selenium.webdriver.support import expected_conditions as EC
import requests
browser = webdriver.Chrome(executable_path=r'./chromedriver')
contents = []
with open('ClassPasslite.csv', 'rt') as cp_csv:
cp_url = csv.reader(cp_csv)
for row in cp_url:
links = row[0]
contents.append(links)
#link should be something like "https://www.classpass.com/studios/forever-body-coaching-london?search-id=49534025882004019"
for link in contents:
browser.get(link)
# paste the code you have here
Tip: Don't forget that browsers take some time to load pages. Adding some time.sleep(3) will help you a lot.

Related

How to scrape news articles from cnbc with keyword "Green hydrogen"?

I am trying to scrap news article listed in this url, all article are in span.Card-title. But this gives blank output. Is there any to resolve this?
from bs4 import BeautifulSoup as soup
import requests
cnbc_url = "https://www.cnbc.com/search/?query=green%20hydrogen&qsearchterm=green%20hydrogen"
html = requests.get(cnbc_url)
bsobj = soup(html.content,'html.parser')
day = bsobj.find(id="root")
print(day.find_all('span',class_='Card-title'))
for link in bsobj.find_all('span',class_='Card-title'):
print('Headlines : {}'.format(link.text))

The problem is that content is not present on page when it loads initially, only afterwards is it fetched from server using url like this
https://api.queryly.com/cnbc/json.aspx?queryly_key=31a35d40a9a64ab3&query=green%20hydrogen&endindex=0&batchsize=10&callback=&showfaceted=false&timezoneoffset=-240&facetedfields=formats&facetedkey=formats%7C&facetedvalue=!Press%20Release%7C&needtoptickers=1&additionalindexes=4cd6f71fbf22424d,937d600b0d0d4e23,3bfbe40caee7443e,626fdfcd96444f28
and added to page.
Take a look at /json.aspx endpoint in devtools, data seems to be there.

As mentioned in another answer, the data about the articles are loaded using another link, which you can find via the networks tab in devtools. [In chrome, you can open devtools with Ctrl+Shift+I, then go to the networks tab to see requests made, and then click on the name starting with 'json.aspx?...' to see details, then copy the Request URL from Headers section.]
Once you have the Request URL, you can copy it and make the request in your code to get the data:
# dataReqUrl contains the copied Request URL
dataReq = requests.get(dataReqUrl)
for r in dataReq.json()['results']: print(r['cn:title'])
If you don't feel like trying to find that one request in 250+ other requests, you might also try to assemble a shorter form of the url with something like:
# import urllib.parse
# find link to js file with api key
jsLinks = bsobj.select('link[href][rel="preload"]')
jUrl = [m.get('href') for m in jsLinks if 'main' in m.get('href')][0]
jRes = requests.get(jUrl) # request js file api key
# get api key from javascript
qKey = jRes.text.replace(' ', '').split(
'QUERYLY_KEY:'
)[-1].split(',')[0].replace('"', '').strip()
# form url
qParams = {
'queryly_key': qKey,
'query': search_for, # = 'green hydrogen'
'batchsize': 10 # can go up to 100 apparently
}
qUrlParams = urllib.parse.urlencode(qParams, quote_via=urllib.parse.quote)
dataReqUrl = f'https://api.queryly.com/cnbc/json.aspx?{qUrlParams}'
Even though the assembled dataReqUrl is not identical to the copied one, it seems to be giving the same results (I checked with a few different search terms). However, I don't know how reliable this method is, especially compared to the much less convoluted approach with selenium:
# 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
# define chromeDriver_path <-- where you saved 'chromedriver.exe'
cnbc_url = "https://www.cnbc.com/search/?query=green%20hydrogen&qsearchterm=green%20hydrogen"
driver = webdriver.Chrome(chromeDriver_path)
driver.get(cnbc_url)
ctSelector = 'span.Card-title'
WebDriverWait(driver, 5).until(EC.visibility_of_all_elements_located(
(By.CSS_SELECTOR, ctSelector)))
cardTitles = driver.find_elements(By.CSS_SELECTOR, ctSelector)
cardTitles_text = [ct.get_attribute('innerText') for ct in cardTitles]
for c in cardTitles_text: print(c)
In my opinion, this approach is more reliable as well as simpler.

How to download PDF from url in python

Note: This is very different problem compared to other SO answers (Selenium Webdriver: How to Download a PDF File with Python?) available for similar questions.
This is because The URL: https://webice.ongc.co.in/pay_adv?TRACKNO=8262# does not directly return the pdf but in turn makes several other calls and one of them is the url that returns the pdf file.
I want to be able to call the url with a variable for the query param TRACKNO and to be able to save the pdf file using python.
I was able to do this using selenium, but my code fails to work when the browser is used in headless mode and I need it to work in headless mode. The code that I wrote is as follows:
import requests
from urllib3.exceptions import InsecureRequestWarning
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
import time
def extract_url(driver):
advice_requests = driver.execute_script("var performance = window.performance || window.mozPerformance || window.msPerformance || window.webkitPerformance || {}; var network = performance.getEntries() || {}; return network;")
print(advice_requests)
for request in advice_requests:
if(request.get('initiatorType',"") == 'object' and request.get('entryType',"") == 'resource'):
link_split = request['name'].split('-')
if(link_split[-1] == 'filedownload=X'):
print("..... Successful")
return request['name']
print("..... Failed")
def save_advice(advice_url,tracking_num):
requests.packages.urllib3.disable_warnings(category=InsecureRequestWarning)
response = requests.get(advice_url,verify=False)
with open(f'{tracking_num}.pdf', 'wb') as f:
f.write(response.content)
def get_payment_advice(tracking_nums):
options = webdriver.ChromeOptions()
# options.add_argument('headless') # DOES NOT WORK IN HEADLESS MODE SO COMMENTED OUT
driver = webdriver.Chrome(options=options)
for num in tracking_nums:
print(num,end=" ")
driver.get(f'https://webice.ongc.co.in/pay_adv?TRACKNO={num}#')
try:
WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.ID, 'ls-highlight-domref')))
time.sleep(0.1)
advice_url = extract_url(driver)
save_advice(advice_url,num)
except:
pass
driver.quit()
get_payment_advice['8262']
As it can be seen I get all the network calls that the browser makes in the first line of the extract_url function and then parse each request to find the correct one. However this does not work in headless mode
Is there any other way of doing this as this seems like a workaround? If not, can this be fixed to work in headless mode?

I fixed it, i only changed one function. The correct url is in the given page_source of the driver (with beautifulsoup you can parse html, xml etc.):
from bs4 import BeautifulSoup
def extract_url(driver):
soup = BeautifulSoup(driver.page_source, "html.parser")
object_element = soup.find("object")
data = object_element.get("data")
return f"https://webice.ongc.co.in{data}"
The hostname part may can be extracted from the driver.
I think i did not changed anything else, but if it not work for you, I can paste the full code.
Old Answer:
if you print the text of the returned page (print(driver.page_source)) i think you would get a message that says something like:
"Because of your system configuration the pdf can't be loaded"
This is because the requested site checks some preferences to decide if you are a roboter or not. Maybe it helps to change some arguments (screen size, user agent) to fix this. Here are some information about, how to detect a headless browser.
And for the next time you should paste all relevant code into the question (imports) to make it easier to test.

How to download website when URL doesn't change after data addition

I would like to download data from http://ec.europa.eu/taxation_customs/vies/ site. Case is that when I enter data on it through program the URL doesn't change, so file saved on disc has a page same as the one which were opened from the begining without data.Maybe I don't know how to access this site after adding data? I'm new in Python and tried to look for solution but with no result so if there was such issue, please link me. Here's my code. I appreciate all responses:)
import requests
import selenium
import select as something
from selenium import webdriver
from selenium.webdriver.support.ui import Select
import pdfkit
url = "http://ec.europa.eu/taxation_customs/vies/?locale=pl"
driver = webdriver.Chrome(executable_path ="C:\\Users\\Python\\Chromedriver.exe")
driver.get("http://ec.europa.eu/taxation_customs/vies/")
#wait = WebDriverWait(driver, 10)
obj = Select(driver.find_element_by_id("countryCombobox"))
obj = obj.select_by_index(1)
vies_r = requests.get(url)
vies_vat = driver.find_element_by_id("number")
vies_vat.send_keys('U54799909')
vies_verify = driver.find_element_by_id("submit")
vies_verify.click()
path_wkhtmltopdf = r'C:\Users\Python\wkhtmltox\wkhtmltox\bin\wkhtmltopdf.exe'
config = pdfkit.configuration(wkhtmltopdf=path_wkhtmltopdf)
print(driver.current_url)
pdfkit.from_url(driver.current_url, "out.pdf", configuration=config)
Ukalo

How to send key with BeautifulSoup

I created a script with selenium to get given GST NUMBER information. I completed that program and it's giving me required details on output without any problem.
Now I do not want to interact it with chrome browser anymore so I'm trying to do this with BeautilfulSoup.
BeautifulSoup is new for me so I have not much idea to find element and I searched a lot about how to send keys with BeautifulSoup but I'm not getting it.
Now my script is stuck here.
from bs4 import BeautifulSoup
import requests
import urllib.request as urllib2
quote_page = 'https://my.gstzen.in/p/search-taxpayer'
page = urllib2.urlopen(quote_page)
soup = BeautifulSoup(page, 'html.parser')
Now even if I manage to find the gst input element then I'm wondering how do I send keys to it? like the 15 digit gst number with sending enter button code or clicking on "Search GST Details".
If possible, then let me know the solution so I can start my research on it.
Actually, I need to do complete this tonight.
Plus, Here is my script which do the same thing with selenium easily and I want to do the same thing with BeautilfulSoup because I do not want chrome to be run every time while checking the GST and BeautilfulSoup seems interesting.
import selenium
import time
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.keys import Keys
import csv
import requests
#import pyvirtualdisplay
#from pyvirtualdisplay import display
#display = Display(visible=0, size=(800, 600))
#display.start()
browser = webdriver.Chrome('E:\\Chrome Driver\\chromedriver_win32\\chromedriver.exe')
browser.set_window_position(-10000,0)
browser.get('https://my.gstzen.in/p/search-taxpayer/')
with open ('product.csv') as csv_file:
csv_reader = csv.reader(csv_file, delimiter=',')
next(csv_reader)
for row in csv_reader:
name, phone = row
time.sleep(1)
gst = browser.find_element_by_name('gstin')
gst.click()
gst.send_keys(name)
time.sleep(1)
Details = browser.find_element_by_xpath("//*[contains(text(), ' Search GSTIN Details')]")
Details.click()
info = browser.find_element_by_class_name('col-sm-4')
print(info.text)
info2 = browser.find_element_by_xpath('/html/body/div[4]/div/div/div[1]/div[2]/div[2]/div[1]/div[2]')
print(info2.text)
input('Press Enter to quit')
browser.quit()

BeautifulSoup is a library for parsing and formatting, not interacting with web pages. For the latter, if that page requires JavaScript to work, you're stuck using a headless browser.
If it doesn't, you have at least two options:
Watch the Network tab in your browser's developer tools and see if you can recreate the request for the page you want using requests or urllib2
Use mechanize, which is built specifically to work with forms on sites that don't depend on JavaScript
mechanize is a little more work if there's no CSRF token or similar mechanism (though, again, it'll fail if JavaScript is required) and a little less work if there is.

Checking the clickability of an element in selenium using python

I've been trying to write a script which will give me all the links to the episodes present on this page :- http://www.funimation.com/shows/assassination-classroom/videos/episodes
As you can see that the links can be seen in 'Outer HTML', I used selenium and PhantomJS with python.
Link Example: http://www.funimation.com/shows/assassination-classroom/videos/official/karma-time
However, I can't seem to get my code right. I do have a basic Idea of what I want to do. Here's the process :-
1.) Copy the Outer HTML of the very first page and then save it as 'Source_html' file.
2.) Look for links inside this file.
3.) Move to the next page to see rest of the videos and their links.
4.) Repeat the step 2.
This is what my code looks like :
from selenium import webdriver
from selenium import selenium
from bs4 import BeautifulSoup
import time
# ---------------------------------------------------------------------------------------------
driver = webdriver.PhantomJS()
driver.get('http://www.funimation.com/shows/assassination-classroom/videos/episodes')
elem = driver.find_element_by_xpath("//*")
source_code = elem.get_attribute("outerHTML")
f = open('source_code.html', 'w')
f.write(source_code.encode('utf-8'))
f.close()
print 'Links On First Page Are : \n'
soup = BeautifulSoup('source_code.html')
subtitles = soup.find_all('div',{'class':'popup-heading'})
official = 'something'
for official in subtitles:
x = official.findAll('a')
for a in x:
print a['href']
sbtn = driver.find_element_by_link_text(">"):
print sbtn
print 'Entering The Loop Now'
for driver.find_element_by_link_text(">"):
sbtn.click()
time.sleep(3)
elem = driver.find_element_by_xpath("//*")
source_code = elem.get_attribute("outerHTML")
f = open('source_code1.html', 'w')
f.write(source_code.encode('utf-8'))
f.close()
Things I already know :-
soup = BeautifulSoup('source_code.html') won't work, because I need to open this file via python and feed it into BS after that. That I can manage.
That official variable isn't really doing anything. Just helping me start a loop.
for driver.find_element_by_link_text(">"):
Now, this is what I need to fix somehow. I'm not sure how to check if this thing is still clickable or not. If yes, then proceed to next page, get the links, click this again to go to page 3 and repeat the process.
Any help would be appreciated.

You don't need to use BeautifulSoup here at all. Just grab all the links via selenium. Proceed to next page only if the > link is visible. Here is the complete implementation including gathering the links, necessary waits. It should work for any page count:
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
driver = webdriver.PhantomJS()
driver.get("http://www.funimation.com/shows/assassination-classroom/videos/episodes")
wait = WebDriverWait(driver, 10)
links = []
while True:
# wait for the page to load
wait.until(EC.visibility_of_element_located((By.CSS_SELECTOR, "a.item-title")))
# wait until the loading circle becomes invisible
wait.until(EC.invisibility_of_element_located((By.ID, "loadingCircle")))
links.extend([link.get_attribute("href") for link in driver.find_elements_by_css_selector("a.item-title")])
print("Parsing page number #" + driver.find_element_by_css_selector("a.jp-current").text)
# click next
next_link = driver.find_element_by_css_selector("a.next")
if not next_link.is_displayed():
break
next_link.click()
time.sleep(1) # hardcoded delay
print(len(links))
print(links)
For the mentioned in the question URL, it prints:
Parsing page number #1
Parsing page number #2
93
['http://www.funimation.com/shows/assassination-classroom/videos/official/assassination-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/assassination-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/assassination-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/baseball-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/baseball-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/baseball-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/karma-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/karma-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/karma-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/grown-up-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/grown-up-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/grown-up-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/assembly-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/assembly-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/assembly-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/test-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/test-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/test-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/school-trip-time1st-period', 'http://www.funimation.com/shows/assassination-classroom/videos/official/school-trip-time1st-period', 'http://www.funimation.com/shows/assassination-classroom/videos/official/school-trip-time1st-period', 'http://www.funimation.com/shows/assassination-classroom/videos/official/school-trip-time2nd-period', 'http://www.funimation.com/shows/assassination-classroom/videos/official/school-trip-time2nd-period', 'http://www.funimation.com/shows/assassination-classroom/videos/official/school-trip-time2nd-period', 'http://www.funimation.com/shows/assassination-classroom/videos/official/transfer-student-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/transfer-student-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/transfer-student-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/l-and-r-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/l-and-r-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/l-and-r-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/transfer-student-time2nd-period', 'http://www.funimation.com/shows/assassination-classroom/videos/official/transfer-student-time2nd-period', 'http://www.funimation.com/shows/assassination-classroom/videos/official/transfer-student-time2nd-period', 'http://www.funimation.com/shows/assassination-classroom/videos/official/ball-game-tournament-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/ball-game-tournament-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/ball-game-tournament-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/talent-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/talent-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/talent-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/vision-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/vision-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/vision-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/end-of-term-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/end-of-term-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/end-of-term-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/schools-out1st-term', 'http://www.funimation.com/shows/assassination-classroom/videos/official/schools-out1st-term', 'http://www.funimation.com/shows/assassination-classroom/videos/official/schools-out1st-term', 'http://www.funimation.com/shows/assassination-classroom/videos/official/island-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/island-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/island-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/action-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/action-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/action-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/pandemonium-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/pandemonium-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/pandemonium-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/karma-time2nd-period', 'http://www.funimation.com/shows/assassination-classroom/videos/official/karma-time2nd-period', 'http://www.funimation.com/shows/assassination-classroom/videos/official/karma-time2nd-period', 'http://www.funimation.com/shows/deadman-wonderland', 'http://www.funimation.com/shows/deadman-wonderland', 'http://www.funimation.com/shows/riddle-story-of-devil', 'http://www.funimation.com/shows/riddle-story-of-devil', 'http://www.funimation.com/shows/soul-eater', 'http://www.funimation.com/shows/soul-eater', 'http://www.funimation.com/shows/assassination-classroom/videos/official/xx-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/xx-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/xx-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/nagisa-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/nagisa-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/nagisa-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/summer-festival-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/summer-festival-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/summer-festival-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/kaede-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/kaede-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/kaede-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/itona-horibe-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/itona-horibe-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/itona-horibe-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/spinning-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/spinning-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/spinning-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/leader-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/leader-time', 'http://www.funimation.com/shows/assassination-classroom/videos/official/leader-time', 'http://www.funimation.com/shows/deadman-wonderland', 'http://www.funimation.com/shows/deadman-wonderland', 'http://www.funimation.com/shows/riddle-story-of-devil', 'http://www.funimation.com/shows/riddle-story-of-devil', 'http://www.funimation.com/shows/soul-eater', 'http://www.funimation.com/shows/soul-eater']

Basically, I use webelement.is_displayed() to check if it is clickable or not.
isLinkDisplay = driver.find_element_by_link_text(">").is_displayed()

Categories