Created
October 15, 2018 14:17
-
-
Save muffincode/ddf384aac93c29db8268578c4fb8b699 to your computer and use it in GitHub Desktop.
Get language and location for webpages
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.request | |
import html2text | |
import nltk | |
from langdetect import detect | |
from geotext import GeoText | |
# Some websites need headers (source: SO) | |
headers = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11', | |
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', | |
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.3', | |
'Accept-Encoding': 'none', | |
'Accept-Language': 'en-US,en;q=0.8', | |
'Connection': 'keep-alive'} | |
# websites.csv = one url per line | |
file = open("websites.csv", "r") | |
for line in file: | |
try: | |
# URL + Request | |
url = line.rstrip() | |
req = urllib.request.Request(url, None, headers) | |
contents = urllib.request.urlopen(req).read() | |
# Get content from HTML | |
text = html2text.html2text(contents.decode()) | |
# Get locale | |
locale = detect(text) | |
# Get location | |
places = GeoText(text) | |
locations = list(set(places.countries)) | |
locations_string = ','.join(locations) | |
print(url,',',locale,',"',locations_string,'"') | |
except: | |
print(req,',error,error') | |
break |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment