Extract VEP consequence table

conda-env.yml

name: vep-consequence-extract
dependencies:
- beautifulsoup4=4.4.1=py35_0
- libxml2=2.9.3=0
- libxslt=1.1.28=0
- lxml=3.6.0=py35_0
- openssl=1.0.2h=1
- pip=8.1.2=py35_0
- python=3.5.1=0
- readline=6.2=2
- requests=2.10.0=py35_0
- setuptools=23.0.0=py35_0
- sqlite=3.13.0=0
- tk=8.5.18=0
- wheel=0.29.0=py35_0
- xz=5.0.5=1
- zlib=1.2.8=3

extract_vep_consequence_table.py

#!/usr/bin/env python

"""
Quick and dirty script for extracting VEP consequence table, creating a JSON
that maps the VEP consequence to its predicted impact level.

Requirements:
    * Python 3.x
    * requests library
    * BeautifulSoup library
    * lxml library

No Rights Reserved. This script is in the public domain.
"""

__author__ = "Wibowo Arindrarto"

URL = "http://www.ensembl.org/info/genome/variation/predicted_data.html"

import json
import sys

import requests
from bs4 import BeautifulSoup


if __name__ == "__main__":

    res = {}
    html = requests.get(URL).text
    soup = BeautifulSoup(html, "lxml")
    tbody = soup.find(attrs={"id": "consequence_type_table"}).contents[3]
    for table_row in tbody.children:
        cols = list(table_row.children)
        vep_cons = cols[1].text
        impact = cols[5].text.split(".")[-1]
        res[vep_cons] = impact

    json.dump(res, sys.stdout)