Merge pull request #3 from KOBeerose/main

Merging stuff

Author: KOBeerose

.gitignore

@@ -0,0 +1,8 @@
+# .gitignore tells git which files (or patterns) it should ignore. It's usually used to avoid 
+#  committing transient files from your working directory that aren't useful to other collaborators, 
+#  such as compilation products, temporary files IDEs create, etc.
+.ipynb_checkpoints
+*/.ipynb_checkpoints/*
+Information.txt
+*.csv
+!3-Exploratory Data Analysis/datadyalna.csv

Introduction/Data Cell - Overview .pdf 1-Introduction/Data Cell - Overview .pdfIntroduction/Data Cell - Overview .pdf renamed to 1-Introduction/Data Cell - Overview .pdf

@@ -0,0 +1,22 @@
+
+# first of all of should create your own Information.txt file and DELETE THIS ONE OF if you wanna push your code to GitHub 
+# Explaination: there a .gitignore file in which we put all the file and directories that we don't wanna push to GitHub and you definitely don't want your password to be public to anyone.
+# So we can add save our info locally in Infomation.txt file and add it to .gitignore file so that git will ignore it (BE CAREFULL OF SPELLING!)
+# !!! you can change the order but make sure to keep this format or change the code to match it otherwise !!!
+
+
+url: https://www.facebook.com/
+
+email: bot@mail.ai
+
+password: bot@mail.ai
+
+
+
+
+
+
+
+
+
+

…lection/Data Cell - Data Collection .pdf …llection/Data Cell - Data Collection.pdfData Collection/Data Cell - Data Collection .pdf renamed to 2-Data Collection/Data Cell - Data Collection.pdf Data Collection/Data Cell - Data Collection .pdf renamed to 2-Data Collection/Data Cell - Data Collection.pdf

@@ -1,4 +1,5 @@
 
+#importing all the necessary libaries
 from selenium import webdriver
 from selenium.common.exceptions import TimeoutException
 from selenium.webdriver.common.by import By
@@ -10,6 +11,7 @@ class FacebookCrawler:
     LOGIN_URL = 'https://www.facebook.com/login.php?login_attempt=1&lwv=111'
 
     def __init__(self, login, password):
+        # defining the webdriver and config btw this code will be almost the same in all of your selenium scripts
         chrome_options = webdriver.ChromeOptions()
         prefs = {"profile.default_content_setting_values.notifications": 2}
         chrome_options.add_experimental_option("prefs", prefs)

Data Collection/Notebooks/pandas.ipynb 2-Data Collection/Notebooks/pandas.ipynbData Collection/Notebooks/pandas.ipynb renamed to 2-Data Collection/Notebooks/pandas.ipynb

@@ -0,0 +1,62 @@
+#importing all the necessary libaries
+from selenium import webdriver
+from selenium.webdriver.chrome.options import Options
+import time
+import string
+
+url = email = password = ''
+# defining the webdriver and config btw this code will be almost the same in all of your selenium scripts
+chrome_options = webdriver.ChromeOptions()
+
+# !!! blocking browser notifications !!!
+prefs = {"profile.default_content_setting_values.notifications" : 2} 
+chrome_options.add_experimental_option("prefs", prefs)
+
+# starting in maximized window
+chrome_options.add_argument("start-maximized")
+driver = webdriver.Chrome(chrome_options=chrome_options, executable_path="C:\\Users\\taha_\\Downloads\\chromedriver_win32\\chromedriver.exe")
+
+
+# this function gets the user info and save them in variables
+def get_info(filename): 
+    elem_list=["url","email","password"]   # list of expressions preceding the user info
+    with open(filename, 'r') as read_obj: 
+            for line in read_obj:
+                for elem in elem_list:  # Get the value after an expression occurrence
+                    if elem in line:
+                        # save the value in a variable named according to the expression preceding it
+                        globals()[elem] = line.partition(elem+": ")[2].translate({ord(c): None for c in string.whitespace})   
+
+# getting values of the user information
+get_info("C:\\Users\\taha_\\OneDrive - ine.inpt.ma\\Coding\\Data Science\\Data-Science-Cell-Training\\Data Collection\\scripts\\Information.txt")
+print(url, email, password)
+driver.get(url)
+
+mail = driver.find_element_by_name("email")
+mail.send_keys(email)
+
+passwrd = driver.find_element_by_name("pass")
+passwrd.send_keys(password)
+
+
+log = driver.find_element_by_name("login")
+log.click()
+
+time.sleep(.5)
+
+
+driver.get("http://facebook.com/profile.php")
+
+time.sleep(.5)
+
+'''l2= driver.find_element_by_xpath("//div[@class='sej5wr8e']")
+driver.execute_script("arguments[0].scrollIntoView(true);", l2)
+time.sleep(0.5)
+
+button = driver.find_element_by_xpath("//div[@class='rq0escxv l9j0dhe7 du4w35lb j83agx80 pfnyh3mw i1fnvgqd gs1a9yip owycx6da btwxx1t3']")
+button.click()'''
+
+driver.get(driver.current_url+"friends")
+
+# Complete the follwing script to get data about your facebook friends
+# driver.quit()

… Collection/beautiful website/index.html … Collection/beautiful website/index.htmlData Collection/beautiful website/index.html renamed to 2-Data Collection/beautiful website/index.html Data Collection/beautiful website/index.html renamed to 2-Data Collection/beautiful website/index.html

@@ -1,10 +1,10 @@
 import pandas as pd
 
-df = pd.read_html('https://data-science-cell.netlify.app/', )
+df = pd.read_html('https://www.investing.com/crypto/bitcoin/historical-data', )
 df = df[0]
 
 # droping some unncessary data
-df.drop(df.columns[-1], axis=1, inplace=True)
+"""df.drop(df.columns[-1], axis=1, inplace=True)
 
 df.drop(df[df['column'] == 'value'], axis=1, inplace=True)
 
@@ -13,6 +13,7 @@
 print(df)
 
 # saving Dataframe to a csv file
-df.to_csv('data-cell-memebers.csv', index=False)
+df.to_csv('data-cell-memebers.csv', index=False)"""
 
 
+print(df)