Merge pull request #276 from royninja/master

Email Extractor

scripts/Email Extractor/README.md

@@ -0,0 +1,16 @@
+# Email Extractor with Python
+
+This is a script that takes input as a website and collect all the email address into a csv file.
+
+
+### Setup
+ - Install the requirements (refer below)
+ - Run the script by 'python email_extractor.py'
+ - Input the website to collect emails
+
+
+### Requirements
+```pip install -r requirements.txt```
+
+### usage
+```python email_extractor.py```

scripts/Email Extractor/email_extractor.py

@@ -0,0 +1,45 @@
+
+
+import requests
+from bs4 import BeautifulSoup
+import urllib.request
+from email_scraper import scrape_emails
+import pandas as pd
+from google.colab import files
+ 
+
+urlid = input("Enter Website url (i.e.: example.com): ")
+url = "https://"+urlid+"/"
+reqs = requests.get(url)
+soup = BeautifulSoup(reqs.text, 'html.parser')
+ 
+urls = []
+response = []
+email = []
+for link in soup.find_all('a'):
+    urls.append(link.get('href'))
+for i in range(len(urls)):
+  if(urls[i].startswith("https://")):
+    fp = urllib.request.urlopen(url+urls[i])
+    mybytes = fp.read()
+    mystr = mybytes.decode("utf8")
+    fp.close()
+    response.append(scrape_emails(mystr))
+  else:
+    fp = urllib.request.urlopen(url+urls[i])
+    mybytes = fp.read()
+    mystr = mybytes.decode("utf8")
+    fp.close()
+    response.append(scrape_emails(mystr))
+
+for r in range(len(response)):
+  if not response[r]:
+    continue
+  else:
+    email.append(response[r])
+
+df = pd.DataFrame(email, columns=["Email"])
+df.to_csv('email.csv', index=False)
+
+files.download("email.csv")
+

scripts/Email Extractor/requirements.txt

@@ -0,0 +1,6 @@
+pip install requests
+pip install bs4 
+pip install urllib
+pip install email_scraper
+pip install pandas 
+pip install google