Upload 2 files

Daily_Star_fully_scraped.py

@@ -1,85 +1,90 @@
-def get_data(number):
-
-    
-    ##Necessary imports
-    from selenium import webdriver
-    from selenium.webdriver import chrome
-    from selenium.webdriver import ChromeOptions
-    options = ChromeOptions()
-    options.add_argument("enable-automation");
-    options.add_argument("--window-size=1920,1080");
-    options.add_argument("--no-sandbox");
-    options.add_argument("--disable-extensions");
-    options.add_argument("--dns-prefetch-disable");
-    options.add_argument("--disable-gpu");
-    options.add_argument("--headless=new")
-    driver = webdriver.Chrome(options=options)
-    ## Finding Elements by XPATH
-    from selenium.webdriver.common.by import By
-
-    driver.get("https://www.thedailystar.net/tags/road-accident")
-    
-    """
-    Browsing with browser open codes:
-    ##Necessary imports
-    from selenium import webdriver
-    from selenium.webdriver import chrome
-
-    driver = webdriver.Chrome()
-    ## Finding Elements by XPATH
-    from selenium.webdriver.common.by import By
-    driver.get("https://en.prothomalo.com/topic/Road-accident")
-   """ 
-    import time
-    news_list=[]
-    news_link=[]
-    publish_date=[]
-    for i in range(number):
-        #time.sleep(5)
-        if (i+1)!=0 and (i+1)%10==0:
-            last_height = driver.execute_script("return document.body.scrollHeight")
-            driver.execute_script(f"window.scrollTo(0, {last_height-950})")
-            driver.find_element('xpath',f'/html/body/div[3]/div/div/div/div[2]/main/div/div[2]/div/div[5]/div/div/div[1]/div/div[2]/ul/li/a').click()
-            time.sleep(10)
-        txt=driver.find_element('xpath',f'/html/body/div[3]/div/div/div/div[2]/main/div/div[2]/div/div[5]/div/div/div[1]/div/div[1]/div[{i+1}]/div[2]/div[2]/div[2]/h3/a')
-        publish_date.append(driver.find_element('xpath',f'/html/body/div[3]/div/div/div/div[2]/main/div/div[2]/div/div[5]/div/div/div[1]/div/div[1]/div[{i+1}]/div[1]').text)
-        news_list.append(txt.text)
-        news_link.append(txt.get_attribute("href"))   
-
-
-
-    #### Converting the list to a pandas dataframe by converting the list to a dictionary  ###
-    dict={'News Title':news_list,'News Link':news_link,'Publish Date':publish_date}
-    import pandas as pd
-    df=pd.DataFrame(dict)
-
-
-    ############################################### Description Exctraction #################################################
-    from newspaper import Article
-
-
-    text=[]
-    for i in range(len(df)):
-        url = df['News Link'][i]
-        article = Article(url)
-        article.download()
-        article.parse()
-        
-        text.append(article.text)
-
-    df2=df.assign(Description=text)
-
-
-    for p in range(len(df2)):
-        if df2['Publish Date'][p]=="Not available":
-            df2.drop([p],inplace=True)
-    #df2.reset_index()
-
-    df2.reset_index(drop=True,inplace=True)
-
-    df2["Date + Desc"]=df2['Publish Date'] + ".     News Description:"+ df2['Description']
-
-
-    
-    return df2
-    #df3.to_csv('Prothom_Alo_Description.txt',  index=False)
+def get_data(number):
+    print("Running Daily_Star_Fully_Scraped")
+    ##Necessary imports
+    from selenium import webdriver
+    from selenium.webdriver import chrome
+    from selenium.webdriver import ChromeOptions
+    options = ChromeOptions()
+    options.add_argument("enable-automation")
+    options.add_argument("--window-size=1920,1080")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-extensions")
+    options.add_argument("--dns-prefetch-disable")
+    options.add_argument("--disable-gpu")
+    options.add_argument("--headless=new")
+    driver = webdriver.Chrome(options=options)
+    ## Finding Elements by XPATH
+    from selenium.webdriver.common.by import By
+
+    driver.get("https://www.thedailystar.net/news/bangladesh/accidents-fires")
+    ### Extracting first 8 news seperately
+    import time
+    news_list=[]
+    news_link=[]
+    for i in range(2,10):
+        txt=driver.find_element('xpath',f'/html/body/div[3]/div/div/div/div[2]/main/div/div[2]/div/div[1]/div/div/div/div[{i}]/div/div/h3/a')
+        news_list.append(txt.text)
+        news_link.append(txt.get_attribute("href")) 
+    # Rest of the News_title and news link extraction
+    if(number>8):
+        number=number-8
+        import time
+        for i in range(number):
+            #time.sleep(5)
+            if (i+1)!=0 and (i+1)%10==0:
+                last_height = driver.execute_script("return document.body.scrollHeight")
+                driver.execute_script(f"window.scrollTo(0, {last_height-950})")
+                driver.find_element('xpath',f'/html/body/div[3]/div/div/div/div[2]/main/div/div[2]/div/div[3]/div/div/div[1]/div/div[2]/ul/li/a').click()
+                time.sleep(10)
+            txt=driver.find_element('xpath',f'/html/body/div[3]/div/div/div/div[2]/main/div/div[2]/div/div[3]/div/div/div[1]/div/div[1]/div[{i+1}]/div[2]/h3/a')
+            news_list.append(txt.text)
+            news_link.append(txt.get_attribute("href")) 
+    ###### Scraping Publish Date ######
+    publish_date = []
+    for i in range(len(news_link)):
+        driver.get(news_link[i])
+        
+        # Wait for 6 seconds, then stop the page load
+        time.sleep(6)
+        driver.execute_script("window.stop();")
+        
+        try:
+            # Locate and extract the publish date element
+            publish_date_element = driver.find_element('xpath', '/html/body/div[3]/div[2]/div/div/div[2]/main/div/div[2]/div[1]/div[2]/div/div[1]/div[1]/div/div/div[1]/div[2]/div[2]')
+            publish_date.append(publish_date_element.text)
+        except:
+            publish_date.append("Not available")
+    #### Converting the list to a pandas dataframe by converting the list to a dictionary  ###
+    dict={'News Title':news_list,'News Link':news_link,'Publish Date':publish_date}
+    import pandas as pd
+    df=pd.DataFrame(dict)
+    if(number <=8 ):
+        df = df.head(number)
+
+    ############################################### Description Exctraction #################################################
+    print('Description Extraction Started')
+    from newspaper import Article
+
+
+    text=[]
+    for i in range(len(df)):
+        url = df['News Link'][i]
+        article = Article(url)
+        article.download()
+        article.parse()
+        
+        text.append(article.text)
+
+    df2=df.assign(Description=text)
+
+
+    for p in range(len(df2)):
+        if df2['Publish Date'][p]=="Not available":
+            df2.drop([p],inplace=True)
+    #df2.reset_index()
+
+    df2.reset_index(drop=True,inplace=True)
+
+    df2["Date + Desc"]=df2['Publish Date'] + ".     News Description:"+ df2['Description']
+    return df2
+   

Prothom_alo_fully_scraped.py

@@ -1,86 +1,80 @@
-def get_data(number):
-    print("Running Prothom_alo_fully_scraped")
-    ##Necessary imports
-    from selenium import webdriver
-    from selenium.webdriver import chrome
-    from selenium.webdriver import ChromeOptions
-    options = ChromeOptions()
-    options.add_argument("enable-automation");
-    options.add_argument("--window-size=1920,1080");
-    options.add_argument("--no-sandbox");
-    options.add_argument("--disable-extensions");
-    options.add_argument("--dns-prefetch-disable");
-    options.add_argument("--disable-gpu");
-    options.add_argument("--headless=new")
-    driver = webdriver.Chrome(options=options)
-    ## Finding Elements by XPATH
-    from selenium.webdriver.common.by import By
-
-    driver.get("https://en.prothomalo.com/search?q=road%20accident%20dhaka",)
-
-    import time
-    news_list=[]
-    news_link=[]
-    l=0
-    for i in range(number):
-        if i<15:
-            
-            txt=driver.find_element('xpath',f'/html/body/div/div[6]/div/div/div[1]/div[3]/div[{i+1}]/div/div/div[2]/div/h3/a')
-            news_list.append(txt.text)
-            news_link.append(txt.get_attribute("href"))
-        else:
-            if (i-15)%10==0:
-                time.sleep(5)
-                last_height = driver.execute_script("return document.body.scrollHeight")
-                driver.execute_script(f"window.scrollTo(0, {last_height-1200})")
-                try:
-                    
-                    driver.find_element('xpath',f'/html/body/div/div[6]/div/div/div[1]/div[3]/div[{i+1}]/span').click()
-                except:
-                    l=1
-                if l==1:
-                    time.sleep(5)
-                    try:
-                        driver.find_element('xpath',f'/html/body/div/div[6]/div/div/div[1]/div[3]/div[{i+1}]').click()
-                    except:
-                        time.sleep(5)
-                        driver.find_element('xpath',f'/html/body/div/div[6]/div/div/div[1]/div[3]/div[{i+1}]').click()
-                    l=0
-                time.sleep(5)
-            txt=driver.find_element('xpath',f'/html/body/div/div[6]/div/div/div[1]/div[3]/div[{i+1}]/div/div/div[2]/div/h3/a')
-            news_list.append(txt.text)
-            news_link.append(txt.get_attribute("href"))   
-
-    ###### Scraping Publish Date and Description ######
-
-    publish_date=[]
-    text=[]
-    for i in range (len(news_link)):
-        driver.get(news_link[i])
-        try:
-            publish_date.append(driver.find_element('xpath','/html/body/div/div[6]/div/div/div/div[1]/div[1]/div[1]/div[2]/div[2]/div[1]/time/span').text)
-            tmp=""
-            elements = driver.find_elements(By.TAG_NAME, 'p')
-            for e in elements:
-                tmp=tmp+e.text
-            text.append(tmp)
-        except:
-            publish_date.append("Not available")
-            text.append("Not Available")
-        time.sleep(3)
-
-    #### Converting the list to a pandas dataframe by converting the list to a dictionary  ###
-    dict={'News Title':news_list,'News Link':news_link,'Publish Date':publish_date, 'Description':text}
-    import pandas as pd
-    df=pd.DataFrame(dict)
-    df2=df.copy()
-
-
-    for p in range(len(df2)):
-        if df2['Publish Date'][p]=="Not available":
-            df2.drop([p],inplace=True)
-    #df2.reset_index()
-    df2["Date + Desc"]=df2["Publish Date"] + df2["Description"]
-    df2.reset_index(drop=True,inplace=True)
-    return df2
-    #df3.to_csv('Prothom_Alo_Description.txt',  index=False)
+def get_data(number):
+    print("Running Prothom_alo_fully_scraped")
+    ##Necessary imports
+    from deep_translator import GoogleTranslator
+    from selenium import webdriver
+    from selenium.webdriver import chrome
+    from selenium.webdriver import ChromeOptions
+    options = ChromeOptions()
+    options.add_argument("--headless=new")
+    driver = webdriver.Chrome(options=options)
+    ## Finding Elements by XPATH
+    from selenium.webdriver.common.by import By
+
+    driver.get("https://www.prothomalo.com/topic/%E0%A6%B8%E0%A7%9C%E0%A6%95-%E0%A6%A6%E0%A7%81%E0%A6%B0%E0%A7%8D%E0%A6%98%E0%A6%9F%E0%A6%A8%E0%A6%BE")
+
+    import time, math
+    news_list=[]
+    news_link=[]
+    publish_date=[]
+    if number<=15:
+        txt=driver.find_elements(By.CLASS_NAME, "title-link")
+        date=driver.find_elements(By.TAG_NAME, "time")
+        for i in range(number):
+            news_list.append(txt[i].text)
+            news_link.append(txt[i].get_attribute("href"))
+            publish_date.append(date[i].text)
+        
+    else:
+        clck=int((number-25)/15 + 2)
+        for i in range(clck):
+            print(i)
+            time.sleep(10)
+            last_height = driver.execute_script("return document.body.scrollHeight")
+            driver.execute_script(f"window.scrollTo(0, {last_height-850})")
+            button=driver.find_elements(By.CLASS_NAME, "tNj8k")
+            button[0].click()
+        time.sleep(5)
+        txt=driver.find_elements(By.CLASS_NAME, "title-link")
+        date=driver.find_elements(By.TAG_NAME, "time")
+        for i in range(number):
+            news_list.append(txt[i].text)
+            news_link.append(txt[i].get_attribute("href"))
+            publish_date.append(date[i].text)
+
+    ###### Scraping Description modified for translation######
+    text=[]
+    for i in range (len(news_link)):
+        driver.get(news_link[i])
+        try:
+            tmp=""
+            elements = driver.find_elements(By.TAG_NAME, 'p')
+            for i in range(len(elements)):
+                if i>2 and len(tmp+elements[i].text) < 2000:
+                    tmp=tmp+elements[i].text
+                    
+            text.append(tmp)
+        except:
+            text.append("Not Available")
+        time.sleep(5)
+    ## Translation 
+    for i in range(len(news_list)):
+        news_list[i] = GoogleTranslator(source='auto', target='en').translate(text=news_list[i])
+        text[i] = GoogleTranslator(source='auto', target='en').translate(text=text[i])
+        publish_date[i] = GoogleTranslator(source='auto', target='en').translate(text=publish_date[i])
+
+        #### Converting the list to a pandas dataframe by converting the list to a dictionary  ###
+        dict={'News Title':news_list,'News Link':news_link,'Publish Date':publish_date, 'Description':text}
+        import pandas as pd
+        df=pd.DataFrame(dict)
+        df2=df.copy()
+
+
+    for p in range(len(df2)):
+        if df2['Publish Date'][p]=="Not available":
+            df2.drop([p],inplace=True)
+    #df2.reset_index()
+    df2["Date + Desc"]=df2["Publish Date"] + df2["Description"]
+    df2.reset_index(drop=True,inplace=True)
+    return df2
+    #df3.to_csv('Prothom_Alo_Description.txt',  index=False)