Created
October 14, 2020 21:24
-
-
Save symroc/b0687fd036b3d8dff913aacc24bb2e21 to your computer and use it in GitHub Desktop.
Read Google Eearth's kml(or kmz file converted to kml)
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
from bs4 import BeautifulSoup | |
import pandas as pd | |
import numpy as np | |
def remove_html_tags(text): | |
"""Remove html tags from a string""" | |
import re | |
clean = re.compile('<.*?>') | |
return re.sub(clean, '', text) | |
with open ('your directory') as f: | |
doc=f.read() | |
soup = BeautifulSoup(doc, 'xml') | |
locs=soup.find_all("Placemark") | |
# names=locs.find_all("name") | |
names=[] | |
lat=[] | |
long=[] | |
for eachtakeaway in locs: | |
nametag = eachtakeaway.find('name') | |
nametag = remove_html_tags (str(nametag)) | |
loctag = eachtakeaway.find('coordinates') | |
loctag = remove_html_tags (str(loctag)) | |
loctag = loctag[:-2] | |
loc=loctag.split(',') | |
names.append(nametag) | |
lat.append(loc[0]) | |
long.append(loc[1]) | |
data = { | |
'Names': names, | |
'Latitude': lat, | |
'Longitude': long, | |
} | |
df=pd.DataFrame(data) | |
df=df.drop_duplicates() | |
df.to_excel("location.xlsx",index=False) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment