guanjihuan/GitHub_collection_awesome-machine-learning
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Remove unused variable index.

Browse Source 
Fixes #398
This commit is contained in:
cclauss 2017-08-03 08:36:23 +02:00 committed by GitHub
parent 29cc000de0
commit 6532ce45c8
1 changed files with 18 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
scripts/pull_R_packages.py
View File

@ -1,25 +1,29 @@
#!/usr/bin/python
"""
This script will scrape the r-project.org machine learning selection and format the packages
in github markdown style for this awesome-machine-learning repo.
This script will scrape the r-project.org machine learning selection and
format the packages in github markdown style for this
awesome-machine-learning repo.
"""
from pyquery import PyQuery as pq
import urllib
import codecs
text_file = codecs.open("Packages.txt",encoding='utf-8',mode="w")
d = pq(url='http://cran.r-project.org/web/views/MachineLearning.html',opener=lambda url, **kw: urllib.urlopen(url).read())
text_file = codecs.open("Packages.txt", encoding='utf-8', mode="w")
d = pq(url='http://cran.r-project.org/web/views/MachineLearning.html',
opener=lambda url, **kw: urllib.urlopen(url).read())
for e in d("li").items():
package_name = e("a").html()
package_link = e("a")[0].attrib['href']
if '..' in package_link:
package_link = package_link.replace("..",'http://cran.r-project.org/web')
dd = pq(url=package_link,opener=lambda url, **kw: urllib.urlopen(url).read())
package_description = dd("h2").html()
text_file.write(" [%s](%s) - %s \n" % (package_name,package_link,package_description))
# print "* [%s](%s) - %s" % (package_name,package_link,package_description)
index += 1
package_name = e("a").html()
package_link = e("a")[0].attrib['href']
if '..' in package_link:
package_link = package_link.replace("..",
'http://cran.r-project.org/web')
dd = pq(url=package_link, opener=lambda url,
**kw: urllib.urlopen(url).read())
package_description = dd("h2").html()
text_file.write(" [%s](%s) - %s \n" % (package_name, package_link,
package_description))
# print("* [%s](%s) - %s" % (package_name,package_link,
# package_description))