Created
December 12, 2017 18:53
-
-
Save theriley106/a25f2eff3f90297d5b4b61ed86a08843 to your computer and use it in GitHub Desktop.
Net Neutrality Voting
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import bs4 | |
import requests | |
import csv | |
import json | |
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'} | |
res = requests.get('https://www.theverge.com/2017/12/11/16746230/net-neutrality-fcc-isp-congress-campaign-contribution', headers=headers) | |
page = bs4.BeautifulSoup(res.text, 'lxml') | |
dataBase = [] | |
with open('example.csv', 'rb') as f: | |
reader = csv.reader(f) | |
data = list(reader) | |
for var in data: | |
dataBase.append(str(var)) | |
def extractInfo(listItem): | |
vote = 'Unknown' | |
if 'yea' in str(listItem).lower(): | |
vote = "Yes" | |
if 'nay' in str(listItem).lower(): | |
vote = "No" | |
state = str(listItem).partition("', '")[2].partition("'")[0] | |
return [state, vote] | |
information = {} | |
for i, lpage in enumerate(page.select('table')): | |
for member in lpage.select('tr'): | |
try: | |
column = member.select('td') | |
if 'Member Name' not in str(column): | |
vote = 'Unknown' | |
name = ' '.join(str(column[0].getText()).split(", ")[::-1]) | |
if str(name).count(' ') == 2: | |
firstName = name.split(' ')[0] | |
lastName = name.split(' ')[2] | |
name = ' '.join([firstName, lastName]) | |
if i == 0: | |
party = column[2].getText() | |
else: | |
party = column[1].getText() | |
found = False | |
for value in dataBase: | |
if name in str(value): | |
found = True | |
state, vote = extractInfo(value) | |
if found == False: | |
for value in dataBase: | |
if name.partition(' ')[2] in str(value): | |
found = True | |
state, vote = extractInfo(value) | |
if found == False: | |
if i == 0: | |
state = column[1].getText() | |
else: | |
state = str(column[2].getText())[:2] | |
if party.lower() == 'd': | |
party = "Democrat" | |
if party.lower() == 'r': | |
party = "Republican" | |
if i == 0: | |
#this indicates it's a state representative | |
information[name] = {"Position": "US Senate", "State": state, "Party": party, "Contributions": column[3].getText(), "Vote": vote} | |
else: | |
#this means it's a house of representative | |
information[name] = {"Position": "House of Representatives", "State": state, "Party": party, "Contributions": column[3].getText(), "Vote": vote} | |
except Exception as exp: | |
print exp | |
pass | |
with open('result.json', 'w') as fp: | |
json.dump(information, fp) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment