link extractor project script

extract_repo.py

# downlaod links from dynamoDB
!aws dynamodb scan --table-name Movies --query "Items[*].[id.S,title.S]" --output json | sort -u > /tmp/download.txt

# copy github links and extract repo URLs
import pandas as pd
mylist = """
        "https://github.com/apoorvnandan/speech-recognition-primer"
        "https://github.com/asmitakulkarni/QuoteGenerator"
        "https://github.com/cjhutto/vaderSentiment"
        "https://github.com/docker/docker-bench-security"
"""

finallist = list()
for i in mylist.split():
    finallist.append(i.strip('"').split("/")[3:5])
    
df = pd.DataFrame(finallist)
df = df.drop_duplicates()

for i in df.values:
    print("http://github.com/{0}/{1}".format(i[0], i[1]))