Created
May 20, 2013 01:49
-
-
Save ruliarmando/5609955 to your computer and use it in GitHub Desktop.
python script for scrapping a page
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests | |
from bs4 import BeautifulSoup as Sup | |
page_url = "http://www.bi.go.id/biweb/Templates/Moneter/Default_Kurs_EN.aspx?NRMODE=Published&NRNODEGUID=%7bEC4BBAA9-A1A8-4A4F-AC22-EDDA954C1B6A%7d&NRORIGINALURL=%2fweb%2fen%2fMoneter%2fKurs%2bBank%2bIndonesia%2fKurs%2bTransaksi%2f&NRCACHEHINT=Guest" | |
payload = { | |
'__VIEWSTATE' : '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', | |
'keyword' : 'Search..', | |
'optcurrencies2' : 'GBP', | |
'stgl2' : '1', | |
'sbln2' : '1', | |
'sthn2' : '2013', | |
'etgl2' : '1', | |
'ebln2' : '3', | |
'ethn2' : '2013', | |
'Submit4' : 'Search', | |
'stgl1c' : '1', | |
'sbln1c' : '1', | |
'sthn1c' : '2013' | |
} | |
r = requests.post(page_url, data=payload) | |
sup = Sup(r.text) | |
tables = sup.select('table') | |
kurs_table = tables[22] | |
html = """ | |
<!doctype html> | |
<html> | |
<head> | |
<title>scrapping bi</title> | |
</head> | |
<body> | |
%s | |
</body> | |
</html> | |
""" % kurs_table | |
f = open('scrap.html', 'w') | |
f.write(html) | |
f.close() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment