import sys,os |
import sys,os |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) |
import scrape |
import genericScrapers |
foidocsdb = scrape.couch['disclosr-foidocuments'] |
#RSS feed not detailed |
|
|
#RSS feed not detailed |
#http://www.doughellmann.com/PyMOTW/abc/ |
from bs4 import BeautifulSoup |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): |
#http://www.apvma.gov.au/about/foi/disclosure/index.php |
def getAgencyID(self): |
agencyID = "3cd40b1240e987cbcd3f0e67054ce259" |
return "3cd40b1240e987cbcd3f0e67054ce259" |
(url,mime_type,content) = scrape.fetchURL(scrape.docsdb, "http://www.apvma.gov.au/about/foi/disclosure/index.php", "foidocuments", agencyID) |
|
if content != None: |
|
if mime_type == "text/html" or mime_type == "application/xhtml+xml" or mime_type =="application/xml": |
|
# http://www.crummy.com/software/BeautifulSoup/documentation.html |
|
soup = BeautifulSoup(content) |
|
for row in soup.table.find_all('tr'): |
|
columns = row.find_all('td') |
|
if len(columns) == 5: |
|
(id, date, description, title, notes) = columns |
|
print id.string |
|
hash = scrape.mkhash(url+id.string) |
|
links = [] |
|
for atag in row.find_all("a"): |
|
if atag.has_key('href'): |
|
links.append(scrape.fullurl(url,atag['href'])) |
|
doc = foidocsdb.get(hash) |
|
descriptiontxt = "" |
|
for string in description.stripped_strings: |
|
descriptiontxt = descriptiontxt + string |
|
if doc == None: |
|
print "saving" |
|
doc = {'_id': hash, 'agencyID': agencyID, 'url': url, "links": links, 'docID': id.string, "date": date.string, "description": descriptiontxt,"title": title.string,"notes": notes.string} |
|
foidocsdb.save(doc) |
|
else: |
|
print "already saved" |
|
elif len(row.find_all('th')) == 5: |
|
print "header row" |
|
else: |
|
print "ERROR number of columns incorrect" |
|
print row |
|
|
|
|
def getURL(self): |
|
return "http://www.apvma.gov.au/about/foi/disclosure/index.php" |
|
|
|
def getColumns(self,columns): |
|
(id, date, description, title, notes) = columns |
|
return (id, date, description, title, notes) |
|
|
|
if __name__ == '__main__': |
|
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) |
|
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) |
|
ScraperImplementation().doScrape() |