How to use get_unique_links method in SeleniumBase

Best Python code snippet using SeleniumBase

textSummarization.py

Source:textSummarization.py

...44    summary_list = [str(sentence) for sentence in summary]45    result = " ".join(summary_list)46    return result47regex = 'https.\/\/\S+.html'48def get_unique_links(res):49    links = re.findall(regex,res)50    links = set(links)51    return links52def main():53    '''NLP App'''54    st.title("Text Summarization")55    msg = st.text_area("Eter your data to be summarized","Type here..")56    msg = msg.strip()57    summary_options = st.selectbox("Choice your Summarizer",("Summarizer - 1","Summarizer - 2"))58    try:59        if st.button("Summarize"):60            if summary_options == 'Summarizer - 1':61                result = summarize(msg)62                st.subheader("Summary")63                links = get_unique_links(result)64                result = re.sub('https.\/\/\S+.html', ' ', result)65                result = re.sub(' +', ' ', result)66                a = result.split('. ')67                b = copy.deepcopy(a)68                result = optimize_summary(a, b)69                result = ". ".join(result)70                if len(result) > 2:71                    st.success(result)72                else:73                    st.warning('Feed more data as input to Summarizer Tool')74                t = calc_time(result)75                d = calc_time(msg)76                st.info("Actual data - {} seconds read, Summarised data - {} seconds read".format(d.seconds, t.seconds))77            else:78                st.subheader("Summary")79                result = sumy_summarizer(msg)80                links = get_unique_links(result)81                result = re.sub('https.\/\/\S+.html', ' ', result)82                result = re.sub(' +', ' ', result)83                a=result.split('. ')84                b=copy.deepcopy(a)85                result = optimize_summary(a,b)86                result = ". ".join(result)87                st.success(result)88                t = calc_time(result)89                d = calc_time(msg)90                st.info("Actual data - {} seconds read, Summarised data - {} seconds read".format(d.seconds,t.seconds))91    except:...

chapter03.py

Source:chapter03.py

...36#     print(new_article)37#     links = get_links(new_article)38# Avoid crawling the same page twice39# pages = set()40# def get_unique_links(page_url):41#     global pages42#     html = urlopen("http://en.wikipedia.org{}".format(page_url))43#     bs = BeautifulSoup(html, "html.parser")44#     try:45#         print(bs.h1.get_text())46#         print(bs.find(id="mw-content-text").find_all("p")[0])47#         print(bs.find(id="ca-edit").find("span").find("a").attrs["href"])48#     except AttributeError:49#         print("This page is missing something! Continuing.")50#     for link in bs.find_all("a", href=re.compile("^(/wiki/)")):51#         if "href" in link.attrs:52#             if link.attrs["href"] not in pages:53#                 # Encountered a new page54#                 new_page = link.attrs["href"]55#                 print("-" * 20)56#                 print(new_page)57#                 pages.add(new_page)58#                 get_unique_links(new_page)...

main.py

Source:main.py

...6        self.location = location7        self.links = links8    def update_links(self, new_links):9        combined_links = self.links + new_links10        self.links = get_unique_links(combined_links)11def start_driver():12    return webdriver.Firefox(executable_path="/bin/geckodriver")13    # Starts the web browser using Firefox (namely, gecko)14def end_driver(driver):15    driver.quit()16    # Closes the web browser17def get_links(driver):18    tmp = []19    links = driver.find_elements_by_css_selector('a[href]:not(article a)')20    for link in links:21        link = link.get_attribute('href')22        link = trim_link(link)23        tmp.append(link)24    return tmp25    # Returns a list of objects, each pointing to a link, a[href], that is not an article26def get_unique_links(links):27    unique_links = []28    for link in links:29        if link not in unique_links:30            unique_links.append(link)31    return unique_links32def trim_link(link):33    cleaned_link = link34    if 'http' in cleaned_link:35        cleaned_link = link.split('//', 2)[1]36        cleaned_link = "https://" + cleaned_link37    if cleaned_link[-1] == '/':38        cleaned_link = cleaned_link[0:-1]39    return cleaned_link40if __name__ == "__main__":41    seed = 'https://www.vnq.org.au/'42    browser = start_driver()43    browser.get(seed)44    links = get_links(browser)45    unique_links = get_unique_links(links)46    print(unique_links)47    links_to_check = unique_links48    links_checked = []49    # for link in links_to_check:50    #     browser.get(link)51    #52    #     new_links = get_links(browser)53    #     new_unique_links = get_unique_links(new_links)54    #55    #     links_checked.append(link)56    #     links_to_check.pop(0)...

Automation Testing Tutorials

Learn to execute automation testing from scratch with LambdaTest Learning Hub. Right from setting up the prerequisites to run your first automation test, to following best practices and diving deeper into advanced test scenarios. LambdaTest Learning Hubs compile a list of step-by-step guides to help you be proficient with different test automation frameworks i.e. Selenium, Cypress, TestNG etc.