| 1 | 1 | | from googlesearch import search |
| | 2 | + | from datetime import datetime |
| 2 | 3 | | import requests,re,PyPDF2,tabula,os |
| 3 | 4 | | |
| 4 | 5 | | def PDFcheck(mail,_verbose=None): |
| 5 | 6 | | domain = mail.split("@")[1] |
| 6 | 7 | | term = "site:"+domain+" filetype:PDF intext:"+'"'+"email"+'"' |
| | 8 | + | emails = "" |
| 7 | 9 | | try: |
| 8 | 10 | | data = search(term, num_results=5) |
| 9 | 11 | | for i in data: |
| skipped 10 lines |
| 20 | 22 | | if(findPDFs[0] is not None): |
| 21 | 23 | | for pdfs in findPDFs: |
| 22 | 24 | | print(pdfs) |
| | 25 | + | emails = emails + "\n" + pdfs |
| | 26 | + | with open((datetime.today().strftime('%Y-%m-%d-'+domain)+".txt"), "w") as f: |
| | 27 | + | f.write(emails) |
| | 28 | + | f.close() |
| 23 | 29 | | except: |
| 24 | 30 | | pass |
| 25 | 31 | | pdfFileObj.close() |
| skipped 4 lines |
| 30 | 36 | | os.remove("out.txt") |
| 31 | 37 | | except: |
| 32 | 38 | | print("PDF Search error!") |
| | 39 | + | |
