Created
April 11, 2021 14:43
-
-
Save thisismattmiller/7206277ad137daf9aef9024f6d9b4490 to your computer and use it in GitHub Desktop.
Download yahoo answers sitemap
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 requests | |
import xml.etree.ElementTree as ET | |
import json | |
import multiprocessing | |
answer_urls = [] | |
def do_work(url): | |
print(url) | |
urls = [] | |
r = requests.get(url) | |
file_root = ET.fromstring(r.text) | |
for child in file_root: | |
for loc in child: | |
urls.append(loc.text) | |
return urls | |
if __name__ == "__main__": | |
allxml_requests = requests.get('https://answers.yahoo.com/sitemaps/sitemap-us.xml') | |
root = ET.fromstring(allxml_requests.text) | |
urls_top_level = [] | |
for sitemap in root: | |
for s in sitemap: | |
if s.tag == '{http://www.sitemaps.org/schemas/sitemap/0.9}loc': | |
urls_top_level.append(s.text) | |
the_pool = multiprocessing.Pool(int(multiprocessing.cpu_count())) | |
for results in the_pool.imap_unordered(do_work, urls_top_level): | |
answer_urls = answer_urls + results | |
print(len(answer_urls)) | |
the_pool.close() | |
the_pool.join() | |
json.dump(answer_urls,open('yahoo_answers.json','w'),indent=2) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment