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
sitemap_index_url="https://www.practicalecommerce.com/sitemapindex.xml" | |
from bs4 import BeautifulSoup | |
import requests | |
sitemap_index = {} | |
r = requests.get(sitemap_index_url) | |
xml = r.text | |
soup = BeautifulSoup(xml) | |
sitemapTags = soup.find_all("sitemap") | |
print("The number of sitemaps are {0}".format(len(sitemapTags))) | |
for sitemap in sitemapTags: | |
sitemap_index[sitemap.findNext("loc").text] = sitemap.findNext("lastmod").text | |
print(sitemap_index) | |
#The number of sitemaps are 11 | |
#{'https://www.practicalecommerce.com/site.xml': '2019-07-21T13:42:53Z', 'https://www.practicalecommerce.com/post_part1.xml': '2019-07-21T16:39:21Z', 'https://www.practicalecommerce.com/post_part2.xml': '2019-07-21T09:11:55Z', 'https://www.practicalecommerce.com/post_part3.xml': '2019-07-21T13:43:53Z', 'https://www.practicalecommerce.com/post_seminars.xml': '2019-07-21T13:41:18Z', 'https://www.practicalecommerce.com/post_wpbdp_listing.xml': '2019-07-21T13:46:39Z', 'https://www.practicalecommerce.com/post_google_news.xml': '2019-07-21T17:42:10Z', 'https://www.practicalecommerce.com/page.xml': '2019-07-21T13:46:23Z', 'https://www.practicalecommerce.com/taxonomy_category.xml': '2019-07-21T13:41:48Z', 'https://www.practicalecommerce.com/taxonomy_post_tag.xml': '2019-07-21T13:42:39Z', 'https://www.practicalecommerce.com/author.xml': '2019-07-21T13:41:34Z'} | |
sitemaps = dict() | |
paths = list() | |
lastmods = list() | |
for (sitemap_url, lasmod) in sitemap_index.items(): | |
if(sitemap_url.find("post") > 0): | |
print(sitemap_url) | |
if 1: # for testing | |
r = requests.get(sitemap_url) | |
xml = r.text | |
soup = BeautifulSoup(xml) | |
URLTags = soup.find_all("url") | |
print("The number of URLs are {0}".format(len(URLTags))) | |
for URL in URLTags: | |
if URL.findNext("lastmod"): | |
url = URL.findNext("loc").text | |
parsed_url = urlparse(url) | |
paths.append(parsed_url.path) | |
lastmods.append(URL.findNext("lastmod").text) | |
#sitemaps[parsed_url.path] = URL.findNext("lastmod").text | |
#print(xml_sitemap) #for testing | |
sitemaps["path"] = paths | |
sitemaps["lastmod"] = lastmods | |
#https://www.practicalecommerce.com/post_part1.xml | |
#The number of URLs are 2500 | |
#https://www.practicalecommerce.com/post_part2.xml | |
#The number of URLs are 2500 | |
#https://www.practicalecommerce.com/post_part3.xml | |
#The number of URLs are 1301 | |
#https://www.practicalecommerce.com/post_seminars.xml | |
#The number of URLs are 10 | |
#https://www.practicalecommerce.com/post_wpbdp_listing.xml | |
#The number of URLs are 1162 | |
#https://www.practicalecommerce.com/post_google_news.xml | |
#The number of URLs are 1 | |
#https://www.practicalecommerce.com/taxonomy_post_tag.xml | |
#The number of URLs are 4 | |
import pandas as pd | |
df = pd.DataFrame.from_dict(sitemaps) | |
df.head(10) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment