| DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )" | |
| cd $DIR | |
| echo "" > /tmp/disclosr-error | echo "" > /tmp/disclosr-error |
| for f in scrapers/*.py; do | for f in scrapers/*.py; do |
| echo "Processing $f file.."; | echo "Processing $f file.."; |
| md5=`md5sum /tmp/disclosr-error` | md5=`md5sum /tmp/disclosr-error` |
| python $f 3>&1 1>&2 2>&3 | tee --append /tmp/disclosr-error; | python $f 3>&1 1>&2 2>&3 | tee --append /tmp/disclosr-error; |
| md52=`md5sum /tmp/disclosr-error` | md52=`md5sum /tmp/disclosr-error` |
| if [ "$md5" != "$md52" ]; then | if [ "$md5" != "$md52" ]; then |
| echo "^^^^^^^^^^^^^^ $f" >> /tmp/disclosr-error; | echo "^^^^^^^^^^^^^^ $f" >> /tmp/disclosr-error; |
| fi | fi |
| if [ "$?" -ne "0" ]; then | if [ "$?" -ne "0" ]; then |
| echo "error"; | echo "error"; |
| sleep 1; | sleep 1; |
| fi | fi |
| done | done |
| if [ -s /tmp/disclosr-error ] ; then | if [ -s /tmp/disclosr-error ] ; then |
| echo "emailling logs.."; | echo "emailling logs.."; |
| mail -E -s "Disclosr errors" maxious@lambdacomplex.org < /tmp/disclosr-error ; | mail -E -s "Disclosr errors" maxious@lambdacomplex.org < /tmp/disclosr-error ; |
| fi | fi |
| 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 genericScrapers | import genericScrapers |
| import scrape | import scrape |
| from bs4 import BeautifulSoup | from bs4 import BeautifulSoup |
| import dateutil | import dateutil |
| from dateutil.parser import * | from dateutil.parser import * |
| from datetime import * | from datetime import * |
| #http://www.doughellmann.com/PyMOTW/abc/ | #http://www.doughellmann.com/PyMOTW/abc/ |
| class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper): |
| def getTable(self,soup): | |
| return soup.find(class_ = "inner-column").table | |
| def getRows(self,table): | |
| return table.tbody.find_all('tr',recursive=False) | |
| def getColumnCount(self): | def getColumnCount(self): |
| return 3 | return 0 |
| def getColumns(self,columns): | |
| (date, title, description) = columns | |
| return (date, date, title, description, None) | |
| def getDate(self, content, entry, doc): | |
| i = 0 | |
| date = "" | |
| for string in content.stripped_strings: | |
| if i ==1: | |
| date = string | |
| i = i+1 | |
| edate = parse(date, dayfirst=True, fuzzy=True).strftime("%Y-%m-%d") | |
| print edate | |
| doc.update({'date': edate}) | |
| return | |
| def getTitle(self, content, entry, doc): | |
| i = 0 | |
| title = "" | |
| for string in content.stripped_strings: | |
| if i < 2: | |
| title = title + string | |
| i = i+1 | |
| doc.update({'title': title}) | |
| #print title | |
| return | |
| if __name__ == '__main__': | if __name__ == '__main__': |
| #http://www.csiro.au/Portals/About-CSIRO/How-we-work/Governance/FOI-Request-Disclosure-Log-2012-13.aspx | #http://www.csiro.au/Portals/About-CSIRO/How-we-work/Governance/FOI-Request-Disclosure-Log-2012-13.aspx |
| #http://www.csiro.au/Portals/About-CSIRO/How-we-work/Governance/FOI-Request-Disclosure-Log-2011-12.aspx | #http://www.csiro.au/Portals/About-CSIRO/How-we-work/Governance/FOI-Request-Disclosure-Log-2011-12.aspx |
| print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericHTMLDisclogScraper) |
| print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericHTMLDisclogScraper) |
| ScraperImplementation().doScrape() | ScraperImplementation().doScrape() |
| import sys | import sys |
| import os | import 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 genericScrapers | import genericScrapers |
| import scrape | import scrape |
| from datetime import date | from datetime import date |
| from pyquery import PyQuery as pq | from pyquery import PyQuery as pq |
| from lxml import etree | from lxml import etree |
| import urllib | import urllib |
| import dateutil | import dateutil |
| from dateutil.parser import * | from dateutil.parser import * |
| class ACMADisclogScraper(genericScrapers.GenericDisclogScraper): | class ACMADisclogScraper(genericScrapers.GenericDisclogScraper): |
| def doScrape(self): | def doScrape(self): |
| foidocsdb = scrape.couch['disclosr-foidocuments'] | foidocsdb = scrape.couch['disclosr-foidocuments'] |
| (url, mime_type, content) = scrape.fetchURL(scrape.docsdb, | (url, mime_type, content) = scrape.fetchURL(scrape.docsdb, |
| self.getURL(), "foidocuments", self.getAgencyID()) | self.getURL(), "foidocuments", self.getAgencyID()) |
| d = pq(content) | d = pq(content) |
| d.make_links_absolute(base_url = self.getURL()) | d.make_links_absolute(base_url = self.getURL()) |
| for table in d('table').items(): | for table in d('table').items(): |
| title= table('thead').text() | title= table('thead').text() |
| print title | print self.remove_control_chars(title) |
| (idate,descA,descB,link,deldate,notes) = table('tbody tr').map(lambda i, e: pq(e).children().eq(1).text()) | (idate,descA,descB,link,deldate,notes) = table('tbody tr').map(lambda i, e: pq(e).children().eq(1).text()) |
| links = table('a').map(lambda i, e: pq(e).attr('href')) | links = table('a').map(lambda i, e: pq(e).attr('href')) |
| description = descA+" "+descB | description = descA+" "+descB |
| try: | try: |
| edate = parse(idate[:12], dayfirst=True, fuzzy=True).strftime("%Y-%m-%d") | edate = parse(idate[:12], dayfirst=True, fuzzy=True).strftime("%Y-%m-%d") |
| except ValueError: | except ValueError: |
| edate = date.today().strftime("%Y-%m-%d") | edate = date.today().strftime("%Y-%m-%d") |
| pass | pass |
| print edate | print edate |
| dochash = scrape.mkhash(self.remove_control_chars(title)) | dochash = scrape.mkhash(self.remove_control_chars(title)) |
| doc = foidocsdb.get(dochash) | doc = foidocsdb.get(dochash) |
| if doc is None: | if doc is None: |
| print "saving " + dochash | print "saving " + dochash |
| edate = date.today().strftime("%Y-%m-%d") | edate = date.today().strftime("%Y-%m-%d") |
| doc = {'_id': dochash, 'agencyID': self.getAgencyID() | doc = {'_id': dochash, 'agencyID': self.getAgencyID() |
| , 'url': self.getURL(), 'docID': dochash, | , 'url': self.getURL(), 'docID': dochash, |
| "links": links, | "links": links, |
| "date": edate, "notes": notes, "title": title, "description": description} | "date": edate, "notes": notes, "title": title, "description": description} |
| #print doc | #print doc |
| foidocsdb.save(doc) | foidocsdb.save(doc) |
| else: | else: |
| print "already saved" | print "already saved" |
| if __name__ == '__main__': | if __name__ == '__main__': |
| print 'Subclass:', issubclass(ACMADisclogScraper, | print 'Subclass:', issubclass(ACMADisclogScraper, |
| genericScrapers.GenericDisclogScraper) | genericScrapers.GenericDisclogScraper) |
| print 'Instance:', isinstance(ACMADisclogScraper(), | print 'Instance:', isinstance(ACMADisclogScraper(), |
| genericScrapers.GenericDisclogScraper) | genericScrapers.GenericDisclogScraper) |
| ACMADisclogScraper().doScrape() | ACMADisclogScraper().doScrape() |