Created
August 25, 2011 16:44
-
-
Save ymotongpoo/1171120 to your computer and use it in GitHub Desktop.
extract python package name and download counts from PyPI
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 -*- | |
from lxml import etree | |
from StringIO import StringIO | |
from multiprocessing import Pool | |
import urllib2 | |
base_url = r"http://pypi.python.org" | |
xhtml_ns = r'http://www.w3.org/1999/xhtml' | |
pypi_list = r"http://pypi.python.org/pypi?%3Aaction=index" | |
user_agent = ('"User-Agent","value":"Mozilla/5.0 (Windows NT 5.1) ' + | |
'AppleWebKit/535.1 (KHTML, like Gecko) ' + | |
'Chrome/14.0.835.15 Safari/535.1"') | |
# '//table[@class="list"]/tbody/tr...' doesn't work | |
package_name_xpath = ('//table[@class="list"]/' + | |
'/tr[@class="odd" or @class="even"]/td/a') | |
package_data_xpath = ('//table[@class="list"]/tbody' + | |
'/tr[@class="odd" or @class="even"]/td') | |
update_col = 3 | |
download_col = 6 | |
def extract_packages(pypi_list): | |
req = urllib2.Request(pypi_list) | |
req.add_header('User-Agent', user_agent) | |
p = urllib2.urlopen(req) | |
data = p.read() | |
html = etree.parse(StringIO(data), etree.HTMLParser()) | |
pkg_tags = html.xpath(package_name_xpath, | |
namespace = xhtml_ns) | |
print package_name_xpath | |
print len(pkg_tags) | |
pkg_list = [get_pkg_page(p) for p in pkg_tags] | |
return pkg_list | |
def get_pkg_page(pkg_dom): | |
href = pkg_dom.attrib['href'] | |
pkg_title = pkg_dom.text | |
elements = pkg_title.split() | |
if len(elements) == 1: | |
print "package error", pkg_title | |
return dict(name = pkg_title, | |
ver = None, | |
url = href) | |
else: | |
name = elements[0] | |
ver = ' '.join(elements[1:]) | |
return dict(name = name, | |
ver = ver, | |
url = href) | |
def fetch_pkg_data(pkg_dict): | |
req = urllib2.Request(pkg_link) | |
req.add_header('User-Agent', user_agent) | |
p = urllib2.urlopen(req) | |
data = p.read() | |
html = etree.parse(StringIO(data), etree.HTMLParser()) | |
pkg_data = html.xpath(package_data_xpath, | |
namespace = xhtml_ns) | |
update = pkg_data[update_col].text | |
download = pkg_data[download_col].text | |
return (update, download) | |
def main(pypi_list): | |
pkg_list = extract_packages(pypi_list) | |
for p in pkg_list: | |
p['update'], p['download'] = fetch_pkg_data(p) | |
return pkg_list | |
if __name__ == '__main__': | |
print extract_packages(pypi_list) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment