Fetch top 10 starred repositories of user on GitHub Python :

Prerequisites:  

- python

- urllib2

- BeautifulSoup

We write python scripts to make our task easier which is helps you to fetch top 10 starred repositories of any user on GitHub.You just need Github username .

example: mindstick2010

First access the repository url of user. example:

username = “mindstick2010”, then url =“https://github.com/mindstick2010?tab=repositories”

Now scrape the url page and fetch stars,repository name and repository url using BeautifulSoup. On one page there are 20 repositories,if user has more than 20 repositories,you need a loop to access all the pages by beautifulSoup lib.

The code shown below :

//Python3 script to fetch top 10 starred

//repositories of a user on github

import urllib.request, urllib.parse, urllib.error
import urllib.request, urllib.error, urllib.parse
import http.cookiejar
import requests
from lxml import html
from lxml import etree
from bs4 import BeautifulSoup
import re
import operator

top_limit = 9
def openWebsite():
    username = str(input("enter GitHub username: ")
    repo_dict = {}
    url = "https://github.com/"+username+"?tab=repositories"
    while True:
            urllib2  : https://docs.python.org/2/library/urllib2.html
            BeautifulSoup : https://www.crummy.com/software/BeautifulSoup/bs4/doc/
        cj = http.cookiejar.CookieJar()
        opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cj))
        resp = opener.open(url)
        doc = html.fromstring(resp.read())
        repo_name = doc.xpath('//li[@class="col-12 d-block width-full py-4 border-bottom public 

source"]/div[@class="d-inline-block mb-1"]/h3/a/text()'
        repo_list = []
        for name in repo_name:
            name = ' '.join(''.join(name).split())
            repo_list.append(name)
            repo_dict[name] = 0
        response = requests.get(url)
        soup = BeautifulSoup(response.text, 'html.parser')
        soup = BeautifulSoup(response.text, 'html.parser')
        div = soup.find_all('li', {'class': 'col-12 d-block width-full py-4 border-bottom public 

source'})
        for d in div:
            temp = d.find_all('div',{'class':'f6 text-gray mt-2'})
            for t in temp:
                x = t.find_all('a', attrs={'href': re.compile("^\/[a-zA-Z0-9\-\_\.]+\/[a-zA-Z0-9\.\-

\_]+\/stargazers")})
                if len(x) is not 0:
                    name = x[0].get('href')
                    name = name[len(username)+2:-11]
                    repo_dict[name] = int(x[0].text)
        div = soup.find('a',{'class':'next_page'})
if __name__ == "__main__":
    openWebsite()