Created
July 5, 2019 06:51
-
-
Save justindavies/f260916acca3f9d30f78e4a7594b0fa6 to your computer and use it in GitHub Desktop.
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 urllib, json | |
import glob | |
import os | |
import pymongo | |
from pymongo import MongoClient | |
# Set the latest Block form the API | |
client = MongoClient(os.environ["DB"]) | |
db = client.fundy | |
docs = db.docs | |
filings_cursor = docs.find({}, {"filing": 1, "length": 1, "date": 1}) | |
filings = [] | |
for filing in filings_cursor: | |
if "length" in filing and filing["length"] > 1000: | |
filings.append({"filing": filing["filing"], "date": filing["date"]}) | |
print("Gathered") | |
counter = 1 | |
filename = 1 | |
line = "" | |
for filing in filings: | |
line = line + "<url>\n" | |
line = line + "<loc>http://inkl.in/report/"+ filing["filing"] + "</loc>\n" | |
line = line + "<changefreq>weekly</changefreq>" | |
line = line + "<lastmod>" + str(filing["date"]) + "</lastmod>" | |
line = line + "</url>\n" | |
counter=counter+1 | |
if counter == 50000: | |
counter = 1 | |
print("Writing " + str(filename)) | |
file = open(str(filename) + ".xml", "w") | |
file.write('<?xml version="1.0" encoding="UTF-8"?>\n') | |
file.write('<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">\n') | |
file.write(line) | |
file.write("</urlset>") | |
file.close() | |
filename = filename + 1 | |
line = "" | |
sitemapindex = '<?xml version="1.0" encoding="UTF-8"?>\n' | |
sitemapindex = sitemapindex + '<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">\n' | |
for file in glob.glob('*.xml'): | |
sitemapindex = sitemapindex + '<sitemap>\n' | |
sitemapindex = sitemapindex + ' <loc>http://inkl.in/sitemaps/' + file + '</loc>\n' | |
sitemapindex = sitemapindex + '</sitemap>\n' | |
sitemapindex = sitemapindex + '</sitemapindex>' | |
sitemap = open("map.xml", "w") | |
sitemap.write(sitemapindex) | |
sitemap.close() | |
print(sitemapindex) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment