Last active
October 11, 2017 05:47
-
-
Save priancho/2c66e98c22637dfe9aa9c378d8f26d3f to your computer and use it in GitHub Desktop.
Download Amazon Product Data (small version) directly into HDFS.
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
# Download Amazon Product Data (small version). | |
# For details, see: http://jmcauley.ucsd.edu/data/amazon/ | |
# | |
# Caution! | |
# Before running this download script, create a directiory in | |
# HDFS to save files. Then, set it in BASE_PATH variable. | |
# | |
#--- | |
# Downloading using ipython. | |
#--- | |
import sys | |
from os import path | |
from urllib import request | |
from lxml import html | |
from hdfs3 import HDFileSystem | |
ROOT_URL = 'http://snap.stanford.edu/data/amazon/' | |
CHUNK_SIZE = 10*1024*1024 | |
BASE_PATH = '/user/myaccount/data/amazon_product_data_small' | |
DATASE_XPATH = '//*[@id="main"]/table[1]/tr/td[2]/a' | |
if __name__ == '__main__': | |
# Connect to HDFs | |
hdfs = HDFileSystem() | |
# Open and parse the Web page. | |
doc = html.parse(request.urlopen(ROOT_URL)) | |
# Download datasets. | |
for n in node.xpath(DATASET_XPATH): | |
# Get the URL for a dataset. | |
data_url = n.get('href') | |
filename = path.basename(data_url) | |
# Save it into HDFS directly. | |
print("Getting the data from %s" % (data_url)) | |
response = request.urlopen(data_url) | |
with hdfs.open(path.join(BASE_PATH, filename), 'wb') as f: | |
while True: | |
chunk = response.read(CHUNK_SIZE) | |
if not chunk: | |
sys.stderr.write('\n') | |
break | |
f.write(chunk) | |
sys.stderr.write('.') | |
sys.stderr.flush() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment