| import sys, os | |
| import time | |
| import scrape | |
| from bs4 import BeautifulSoup | |
| from unidecode import unidecode | |
| listurl = "http://gazettes.ag.gov.au/portal/govgazonline.nsf/publications?OpenView&Start=3960" | |
| (url, mime_type, listhtml) = scrape.fetchURL(scrape.docsdb, | |
| listurl, "gazette", "AGD") | |
| soup = BeautifulSoup(listhtml) | |
| for row in soup.find_all('tr'): | |
| if row.has_key('valign'): | |
| for col in tr.find_all('td'): | |
| print col.string | |
| #url = scrape.fullurl(listurl, atag['href']) | |
| #(url, mime_type, html) = scrape.fetchURL(scrape.docsdb, | |
| # url, "data", "AGIMO") | |
| #hash = scrape.mkhash(scrape.canonurl(url)) | |
| #doc = scrape.docsdb.get(hash) | |
| #print doc['metadata'] | |
| #scrape.docsdb.save(doc) | |
| #time.sleep(2) | |