xgi-org / xgi-data Goto Github PK

import requests
import gzip
import pandas as pd
from io import StringIO

# This URL points to one of the files of this dataset: https://zenodo.org/record/2539424
# It is a compressed plain text file containing a directed edge list
url = 'https://zenodo.org/api/files/c2d18dc0-c4ca-4454-aa3e-fd6e035b4f87/dewiki.wikilink_graph.2003-03-01.csv.gz'

# Download the file and make sure everything went ok
r = requests.get(url)
assert r.ok

# decompress (it is a .gz file) and decode (the return type is bytes, not str) and 
data = gzip.decompress(r.content).decode('utf-8')

# Now data is a string with the entire contents of the downloaded file. Since pd.read_csv
# expects a file and not a string, use StringIO to give the data a file-like interface.
# Also, watch the delimiter!
df = pd.read_csv(StringIO(data), delimiter='\t')

df.head()
# page_id_from page_title_from     page_id_to page_title_to
# 0            10   Aussagenlogik  7334       Äquivalenz
# 1            10   Aussagenlogik  767        Boolesche Algebra
# 2            10   Aussagenlogik  1217       Disjunktion
# 3            10   Aussagenlogik  2446       Implikation
# 4            10   Aussagenlogik  2895       Konjunktion