Skip to content

Instantly share code, notes, and snippets.

Embed
What would you like to do?
Simple python script to scrape all geological names from the New Zealand Stratigraphic Lexicon
#!/usr/bin/python
# -*- coding: iso-8859-15 -*-
# python script to scrape all geo names from http://data.gns.cri.nz/stratlex/view.jsp?id=981&page=1
# ~7205 pages so for each id
# on each page get
# <td class="lighter">NAME​/td>â€
# add it to a list and output list as a textfile.dic with on word to a line
# instruction i used http://stackoverflow.com/questions/2081586/web-scraping-with-python
import urllib2
from BeautifulSoup import BeautifulSoup
# or if your're using BeautifulSoup4:
# from bs4 import BeautifulSoup
from random import random
from time import sleep
names=[] # put names here
outFile='nz_strat_units.dic'
outFileObj=open(outFile,'w')
for n in range(7205):
user_agent = 'Mozilla/6 (Solaris %i) Gecko' % random()*10
headers = { 'User-Agent' : user_agent }
sleep(0.02)
url='http://data.gns.cri.nz/stratlex/view.jsp?id=%i' % n
try:
soup = BeautifulSoup(urllib2.urlopen(url).read())
except urllib2.HTTPError, error:
print error.read()
sleep(40)
lights = soup('td', {'class' : 'lighter'})
if lights:
name=lights[1].getText()
names.append(name)
print n, name
outFileObj.write(name+'\n')
outFileObj.close()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment