Created
September 4, 2014 19:34
-
-
Save alecxe/8e14ab756d0b48d8ba30 to your computer and use it in GitHub Desktop.
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
| # -*- coding: utf-8 -*- | |
| import mechanize | |
| import cookielib | |
| b = mechanize.Browser() | |
| b.set_handle_refresh(True) | |
| b.set_debug_redirects(True) | |
| b.set_handle_redirect(True) | |
| b.set_debug_http(True) | |
| cj = cookielib.CookieJar() | |
| b.set_cookiejar(cj) | |
| b.addheaders = [ | |
| ('User-agent', 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2062.94 Safari/537.36'), | |
| ('Accept', 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'), | |
| ('Host', 'www.fangraphs.com'), | |
| ('Referer', 'http://www.fangraphs.com/leaders.aspx?pos=all&stats=bat&lg=all&qual=y&type=8&season=2014&month=0&season1=2014&ind=0') | |
| ] | |
| b.open("http://www.fangraphs.com/leaders.aspx?pos=all&stats=bat&lg=all&qual=y&type=8&season=2014&month=0&season1=2014&ind=0") | |
| def is_form1_form(form): | |
| return "id" in form.attrs and form.attrs['id'] == "form1" | |
| b.select_form(predicate=is_form1_form) | |
| b.form.find_control(name='__EVENTTARGET').readonly = False | |
| b.form.find_control(name='__EVENTARGUMENT').readonly = False | |
| b.form['__EVENTTARGET'] = 'LeaderBoard1$cmdCSV' | |
| b.form['__EVENTARGUMENT'] = '' | |
| print b.submit().read() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I am trying to do what I think you're trying to do here. I am trying to download the .csv files from fangraphs.com. I have a script that works using selenium, but it needs a browser, and I'm looking for a headless solution like this one. When you run this, does it actually download the .csv file somewhere? When I run it, the print command just dumps the HTML content, not the .csv file. Thanks, and nice work!