$ ls
Dockerfile linkextractor.py
$ cat linkextractor.py
#!/usr/bin/env python
import sys
import requests
from bs4 import BeautifulSoup
res = requests.get(sys.argv[-1])
soup = BeautifulSoup(res.text, "html.parser")
for link in soup.find_all("a"):
print(link.get("href"))
$ cat Dockerfile
FROM python
LABEL maintainer="Sawood Alam <@ibnesayeed>"
RUN pip install beautifulsoup4
RUN pip install requests
COPY linkextractor.py /app/
WORKDIR /app
RUN chmod a+x linkextractor.py
ENTRYPOINT ["./linkextractor.py"]
$ docker image build -t ibnesayeed/linkextractor .
Sending build context to Docker daemon 3.072kB
Step 1/8 : FROM python
---> 02d2bb146b3b
Step 2/8 : LABEL maintainer="Sawood Alam <@ibnesayeed>"
---> Using cache
---> dd89829b721d
Step 3/8 : RUN pip install beautifulsoup4
---> Running in 6bbf59305fa9
Collecting beautifulsoup4
Downloading https://files.pythonhosted.org/packages/3b/c8/a55eb6ea11cd7e5ac4bacdf92bac4693b90d3ba79268be16527555e186f0/beautifulsoup4-4.8.1-py3-none-any.whl (101kB)
Collecting soupsieve>=1.2 (from beautifulsoup4)
Downloading https://files.pythonhosted.org/packages/81/94/03c0f04471fc245d08d0a99f7946ac228ca98da4fa75796c507f61e688c2/soupsieve-1.9.5-py2.py3-none-any.whl
Installing collected packages: soupsieve, beautifulsoup4
Successfully installed beautifulsoup4-4.8.1 soupsieve-1.9.5
WARNING: You are using pip version 19.2.3, however version 19.3.1 is available.
You should consider upgrading via the 'pip install --upgrade pip' command.
Removing intermediate container 6bbf59305fa9
---> a8dd8a35998a
Step 4/8 : RUN pip install requests
---> Running in fa8f3870e362
Collecting requests
Downloading https://files.pythonhosted.org/packages/51/bd/23c926cd341ea6b7dd0b2a00aba99ae0f828be89d72b2190f27c11d4b7fb/requests-2.22.0-py2.py3-none-any.whl (57kB)
Collecting urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 (from requests)
Downloading https://files.pythonhosted.org/packages/e0/da/55f51ea951e1b7c63a579c09dd7db825bb730ec1fe9c0180fc77bfb31448/urllib3-1.25.6-py2.py3-none-any.whl (125kB)
Collecting certifi>=2017.4.17 (from requests)
Downloading https://files.pythonhosted.org/packages/18/b0/8146a4f8dd402f60744fa380bc73ca47303cccf8b9190fd16a827281eac2/certifi-2019.9.11-py2.py3-none-any.whl (154kB)
Collecting idna<2.9,>=2.5 (from requests)
Downloading https://files.pythonhosted.org/packages/14/2c/cd551d81dbe15200be1cf41cd03869a46fe7226e7450af7a6545bfc474c9/idna-2.8-py2.py3-none-any.whl (58kB)
Collecting chardet<3.1.0,>=3.0.2 (from requests)
Downloading https://files.pythonhosted.org/packages/bc/a9/01ffebfb562e4274b6487b4bb1ddec7ca55ec7510b22e4c51f14098443b8/chardet-3.0.4-py2.py3-none-any.whl (133kB)
Installing collected packages: urllib3, certifi, idna, chardet, requests
Successfully installed certifi-2019.9.11 chardet-3.0.4 idna-2.8 requests-2.22.0 urllib3-1.25.6
WARNING: You are using pip version 19.2.3, however version 19.3.1 is available.
You should consider upgrading via the 'pip install --upgrade pip' command.
Removing intermediate container fa8f3870e362
---> f7c2a11244df
Step 5/8 : COPY linkextractor.py /app/
---> 8a882e68e727
Step 6/8 : WORKDIR /app
---> Running in ce9b241641d6
Removing intermediate container ce9b241641d6
---> e46946e052ee
Step 7/8 : RUN chmod a+x linkextractor.py
---> Running in 3b995eeec865
Removing intermediate container 3b995eeec865
---> 71b85becc7f1
Step 8/8 : ENTRYPOINT ["./linkextractor.py"]
---> Running in 1806b44bcdaa
Removing intermediate container 1806b44bcdaa
---> aa5f2999d279
Successfully built aa5f2999d279
Successfully tagged ibnesayeed/linkextractor:latest
$ docker container run ibnesayeed/linkextractor https://example.com/
https://www.iana.org/domains/example
