In [1]:
import requests
import pandas as pd

In [3]:
dfs = []
base_url = "https://anc.dc.gov/page/advisory-neighborhood-commission-"
for i in range(1, 9):
    for j in ['a', 'b', 'c', 'd', 'e', 'f', 'g']:
        url = base_url + str(i) + j
        r = requests.get(url)
        if r.status_code == 200:
            df = pd.read_html(r.content, header=None, converters={'SMD': str})
            dfs.append(df[0])

In [4]:
#missing one ANC, 1B due to a 403 error
r = requests.get("https://anc.dc.gov/page/advisory-neighborhood-commission-1b-00")

In [5]:
df = pd.read_html(r.content, header=None)
dfs.append(df[0])

In [6]:
len(dfs) == 40


Out[6]:
True

In [12]:
current_members = pd.concat(dfs, sort=False)

In [18]:
current_members = current_members.set_index('SMD', verify_integrity= True)

In [14]:
current_members.shape


Out[14]:
(297, 5)

In [19]:
current_members.to_csv("current_anc_membership.csv")

In [20]:
current_members.head()


Out[20]:
Name Address Phone Email
SMD
1A01 Layla Bonnot 1434 Parkwood Place NW Washington, DC 20010 NaN 1A01@anc.dc.gov
1A02 Teresa A. Edmondson 1477 Newton St NW Washington, DC 20010 (240) 813-0264 1A02@anc.dc.gov
1A03 Zach Rybarczyk 1400 Irving Street NW Washington, DC 20010 NaN 1A03@anc.dc.gov
1A04 Matthew Goldschimdt 1349 Parkwood Place NW Washington, DC 20010 NaN 1A04@anc.dc.gov
1A05 Christine Miller 1530 Monroe St NW Washington, DC 20010 NaN 1A05@anc.dc.gov

In [ ]:


In [ ]:


In [ ]: