From: Alex Sadleir Date: Fri, 26 Apr 2013 12:41:45 +0000 Subject: tool to check datagov resources X-Git-Url: https://maxious.lambdacomplex.org/git/?p=disclosr.git&a=commitdiff&h=f8e2c3836140f6e9b4f226b93c8b7a5a8cda035f --- tool to check datagov resources Former-commit-id: f406384c3ba09ba04f639abb5731511ddf02b88b --- --- a/admin/refreshDesignDoc.php +++ b/admin/refreshDesignDoc.php @@ -42,6 +42,7 @@ $obj->views->byWebServer->map = "function(doc) {\n emit(doc.web_server, doc);\n}"; $obj->views->datasets->map = "function(doc) {\nif (doc.fieldName == \"data\") {\n emit(doc._id, doc);\n}\n}"; +$obj->views->datasetGroups->map = "function(doc) {\nif (doc.fieldName == \"data\") {\n doc.metadata[\"data.gov.au Category\"] && doc.metadata[\"data.gov.au Category\"].forEach(function(tag) {\n emit(tag, doc.url); \n });\n}\n}"; $obj->views->getValidationRequired->map = "function(doc) {\nif (doc.mime_type == \"text/html\" \n&& typeof(doc.validation) == \"undefined\") {\n emit(doc._id, doc._attachments);\n}\n}"; $docdb->save($obj, true); --- /dev/null +++ b/disclosr.iml @@ -1,1 +1,16 @@ + + + + + + + + + + + + + + + --- /dev/null +++ b/documents/datagov-export-groups.py @@ -1,1 +1,81 @@ +import ckanclient +import couchdb +from ckanclient import CkanApiError +import re + +class LoaderError(Exception): + pass + +# Instantiate the CKAN client. +#ckan = ckanclient.CkanClient(base_location='http://localhost:5000/api', api_key='b47b24cd-591d-40c1-8677-d73101d56d1b') +api_key = 'ff34526e-f794-4068-8235-fcbba38cd8bc' +ckan = ckanclient.CkanClient(base_location='http://data.disclosurelo.gs/api', + api_key=api_key) +couch = couchdb.Server('http://127.0.0.1:5984/') +#couch = couchdb.Server('http://192.168.1.113:5984/') + +# https://github.com/okfn/ckanext-importlib +def munge(name): + # convert spaces to underscores + name = re.sub(' ', '_', name).lower() + # convert symbols to dashes + name = re.sub('[:]', '_-', name).lower() + name = re.sub('[/]', '-', name).lower() + # take out not-allowed characters + name = re.sub('[^a-zA-Z0-9-_]', '', name).lower() + # remove double underscores + name = re.sub('__', '_', name).lower() + return name + + +def name_munge(input_name): + return munge(input_name.replace(' ', '').replace('.', '_').replace('&', 'and')) + + +docsdb = couch['disclosr-documents'] + +if __name__ == "__main__": + groups = {} + for doc in docsdb.view('app/datasetGroups'): + group_name = doc.key + if group_name != "Not specified": + pkg_name = filter(lambda x: x in '0123456789abcdefghijklmnopqrstuvwxyz-_', + doc.value.replace("http://data.gov.au/dataset/", '').replace('/', '')[:100]); + if group_name in groups.keys(): + groups[group_name] = list(set(groups[group_name] + [pkg_name])) + else: + groups[group_name] = [pkg_name] + + # add dataset to group(s) + for group_name in groups.keys(): + if group_name != "Not specified": + group_url = name_munge(group_name[:100]) + print group_name + print groups[group_name] + try: + # Update the group details + group_entity = ckan.group_entity_get(group_url) + print "group "+group_name+" exists" + if 'packages' in group_entity.keys(): + group_entity['packages'] = list(set(group_entity['packages'] + groups[group_name])) + else: + group_entity['packages'] = groups[group_name] + ckan.group_entity_put(group_entity) + except CkanApiError, e: + if ckan.last_status == 404: + print "group "+group_name+" does not exist, creating" + group_entity = { + 'name': group_url, + 'title': group_name, + 'description': group_name, + 'packages': groups[group_name] + } + #print group_entity + ckan.group_register_post(group_entity) + elif ckan.last_status == 409: + print "group already exists" + else: + raise LoaderError('Unexpected status %s adding to group under \'%s\': %r' % ( + ckan.last_status, pkg_name, e.args)) + --- a/documents/datagov-export.py +++ b/documents/datagov-export.py @@ -3,17 +3,45 @@ from ckanclient import CkanApiError import re import html2text # aaronsw :( +import ckanapi # https://github.com/open-data/ckanapi class LoaderError(Exception): pass # Instantiate the CKAN client. -#ckan = ckanclient.CkanClient(base_location='http://localhost:5000/api', api_key='b47b24cd-591d-40c1-8677-d73101d56d1b') -ckan = ckanclient.CkanClient(base_location='http://data.disclosurelo.gs/api', - api_key='482a9dd2-a976-4adf-ac77-d71d92a98a52') +api_key = 'ff34526e-f794-4068-8235-fcbba38cd8bc' +server = 'data.disclosurelo.gs' + +ckan = ckanclient.CkanClient(base_location='http://'+server+'api', + api_key=api_key) +ckandirect = ckanapi.RemoteCKAN('http://'+server, api_key=api_key) couch = couchdb.Server('http://127.0.0.1:5984/') #couch = couchdb.Server('http://192.168.1.113:5984/') + +import urllib +import urlparse + +def url_fix(s, charset='utf-8'): + """Sometimes you get an URL by a user that just isn't a real + URL because it contains unsafe characters like ' ' and so on. This + function can fix some of the problems in a similar way browsers + handle data entered by the user: + + >>> url_fix(u'http://de.wikipedia.org/wiki/Elf (Begriffsklärung)') + 'http://de.wikipedia.org/wiki/Elf%20%28Begriffskl%C3%A4rung%29' + + :param charset: The target charset for the URL if the url was + given as unicode string. + """ + if isinstance(s, unicode): + s = s.encode(charset, 'ignore') + if not urlparse.urlparse(s).scheme: + s = "http://"+s + scheme, netloc, path, qs, anchor = urlparse.urlsplit(s) + path = urllib.quote(path, '/%') + qs = urllib.quote_plus(qs, ':&=') + return urlparse.urlunsplit((scheme, netloc, path, qs, anchor)) # http://code.activestate.com/recipes/578019-bytes-to-human-human-to-bytes-converter/ SYMBOLS = { @@ -24,6 +52,7 @@ 'iec_ext': ('byte', 'kibi', 'mebi', 'gibi', 'tebi', 'pebi', 'exbi', 'zebi', 'yobi'), } + def human2bytes(s): """ @@ -53,6 +82,9 @@ ... ValueError: can't interpret '12 foo' """ + if s == None: + return 0 + s = s.replace(',', '') init = s num = "" while s and s[0:1].isdigit() or s[0:1] == '.': @@ -91,8 +123,6 @@ def name_munge(input_name): return munge(input_name.replace(' ', '').replace('.', '_').replace('&', 'and')) - #[:100] - #return input_name.replace(' ', '').replace('.', '_').replace('&', 'and') def get_licence_id(licencename): @@ -113,87 +143,106 @@ raise Exception(licencename + " not found"); return map[licencename]; + docsdb = couch['disclosr-documents'] if __name__ == "__main__": + orgs_list = [] + orgs_ids = {} for doc in docsdb.view('app/datasets'): + print " --- " print doc.id + if doc.value['url'] != "http://data.gov.au/data/" and doc.value['agencyID'] != "qld": + + # Collect the package metadata. - pkg_name = doc.value['url'].replace("http://data.gov.au/dataset/",'').replace('/',''); + pkg_name = filter(lambda x: x in '0123456789abcdefghijklmnopqrstuvwxyz-_', + doc.value['url'].replace("http://data.gov.au/dataset/", '').replace('/', '')[:100]); + print pkg_name + #add to or create organization using direct API + agency = doc.value['metadata']["Agency"] + if agency == "APS": + agency = "Australian Public Service Commission" + if agency == "Shared Services, Treasury Directorate": + agency = "Shared Services Procurement, Treasury Directorate" + if agency == "Treasury - Shared Services": + agency = "Shared Services Procurement, Treasury Directorate" + if agency == "Territory and Municipal Services (TAMS)": + agency = "Territory and Municipal Services Directorate" + if agency == "State Library of NSW": + agency = "State Library of New South Wales" + org_name = name_munge(agency[:100]) + if org_name not in orgs_list: + orgs_list = ckandirect.action.organization_list()['result'] + #print orgs_list + if org_name not in orgs_list: + try: + print "org not found, creating " + org_name + ckandirect.action.organization_create(name=org_name, title=agency, + description=agency) + orgs_list.append(org_name) + except ckanapi.ValidationError, e: + print e + raise LoaderError('Unexpected status') + else: + print "org found, adding dataset to " + org_name + + # cache org names -> id mapping + if org_name not in orgs_ids: + org = ckandirect.action.organization_show(id=org_name) + orgs_ids[org_name] = org["result"]["id"] + org_id = orgs_ids[org_name] + print "org id is "+org_id tags = [] + creator = doc.value['metadata']["DCTERMS.Creator"] if doc.value['agencyID'] == "AGIMO": if len(doc.value['metadata']["Keywords / Tags"]) > 0: if hasattr(doc.value['metadata']["Keywords / Tags"], '__iter__'): tags = tags + doc.value['metadata']["Keywords / Tags"] else: tags = tags + [doc.value['metadata']["Keywords / Tags"]] - if 'data.gov.au Category' in doc.value['metadata'].keys() and len(doc.value['metadata']['data.gov.au Category']) > 0: - if hasattr(doc.value['metadata']['data.gov.au Category'], '__iter__'): - tags = tags + doc.value['metadata']['data.gov.au Category'] - else: - tags = tags + [doc.value['metadata']['data.gov.au Category']] + tags = [re.sub('[^a-zA-Z0-9-_.]', '', tag.replace('&', 'and')).lower() for tag in tags if tag] - print tags + #print tags + extras = [] + + for extra_key in doc.value['metadata'].keys(): + if extra_key not in ["Description","Content-Language","DCTERMS.Description", "Keywords / Tags" ,"data.gov.au Category", "Download", "Permalink","DCTERMS.Identifier"]: + if doc.value['metadata'][extra_key] != None and doc.value['metadata'][extra_key] != "": + extras.append([extra_key, doc.value['metadata'][extra_key]]) + package_entity = { 'name': pkg_name, 'title': doc.value['metadata']['DCTERMS.Title'], 'url': doc.value['metadata']['DCTERMS.Source.URI'], 'tags': tags, #tags are mandatory? - 'author': doc.value['metadata']["DCTERMS.Creator"], - 'maintainer': doc.value['metadata']["DCTERMS.Creator"], + 'author': creator, + 'maintainer': creator, 'licence_id': get_licence_id(doc.value['metadata']['DCTERMS.License']), 'notes': html2text.html2text(doc.value['metadata']['Description']), + 'owner_org': org_id, + 'extras': extras } - if doc.value['agencyID'] == "qld": - package_entity = doc.value['metadata'] + try: - print package_entity + #print package_entity ckan.package_register_post(package_entity) except CkanApiError, e: - if ckan.last_status == 409: + if ckan.last_message == "{\"name\": [\"That URL is already in use.\"]}": print "package already exists" else: + print ckan.last_message raise LoaderError('Unexpected status %s checking for package under \'%s\': %r' % ( ckan.last_status, pkg_name, e.args)) - - - #add to group - - group_name = name_munge(doc.value['metadata']["Agency"][:100]) - try: - print ckan.group_entity_get(group_name) - - # Update the group details - group_entity = ckan.last_message - print "group exists" - if 'packages' in group_entity.keys(): - group_entity['packages'] = list(set(group_entity['packages'] + [pkg_name])) - else: - group_entity['packages'] = [pkg_name] - ckan.group_entity_put(group_entity) - except CkanApiError, e: - if ckan.last_status == 404: - print "group does not exist, creating" - group_entity = { - 'name': group_name, - 'title': doc.value['metadata']["Agency"], - 'description': doc.value['metadata']["Agency"], - 'packages': [pkg_name], - # 'type': "organization" # not allowed via API, use database query - # update "group" set type = 'organization'; - } - print group_entity - ckan.group_register_post(group_entity) - elif ckan.last_status == 409: - print "group already exists" - else: - raise LoaderError('Unexpected status %s adding to group under \'%s\': %r' % ( - ckan.last_status, pkg_name, e.args)) + pkg = ckan.package_entity_get(pkg_name) + + + # add resources (downloadable data files) if 'Download' in doc.value['metadata'].keys(): try: - pkg = ckan.package_entity_get(pkg_name) + resources = pkg.get('resources', []) if len(resources) < len(doc.value['metadata']['Download']): for resource in doc.value['metadata']['Download']: @@ -205,12 +254,17 @@ format = 'xml' if resource['format'] == '(CSV/XLS)': format = 'csv' + if resource['format'] == '(Shapefile)': + format = 'shp' + if resource['format'] == '(KML/KMZ)': + format = 'kml' name = resource['href'] if 'name' in resource.keys(): name = resource['name'] print resource - ckan.add_package_resource(pkg_name, resource['href'], name=name, resource_type='data', - format=format, size=human2bytes(resource['size'].replace(',', ''))) + ckan.add_package_resource(pkg_name, url_fix(resource['href']), name=name, resource_type='data', + format=format, + size=human2bytes(resource.get('size','0B'))) else: print "resources already exist" except CkanApiError, e: --- /dev/null +++ b/documents/datagov-resourcereport.py @@ -1,1 +1,79 @@ +import couchdb +couch = couchdb.Server('http://127.0.0.1:5984/') +#couch = couchdb.Server('http://192.168.1.113:5984/') +import urllib +import urlparse +import httplib2 +import csv +import ssl + +context = ssl.SSLContext(ssl.PROTOCOL_SSLv23) +context.verify_mode = ssl.CERT_NONE + +def url_fix(s, charset='utf-8'): + """Sometimes you get an URL by a user that just isn't a real + URL because it contains unsafe characters like ' ' and so on. This + function can fix some of the problems in a similar way browsers + handle data entered by the user: + + :param charset: The target charset for the URL if the url was + given as unicode string. + """ + if isinstance(s, unicode): + s = s.encode(charset, 'ignore') + if not urlparse.urlparse(s).scheme: + s = "http://"+s + scheme, netloc, path, qs, anchor = urlparse.urlsplit(s) + path = urllib.quote(path, '/%') + qs = urllib.quote_plus(qs, ':&=') + return urlparse.urlunsplit((scheme, netloc, path, qs, anchor)) + +# http://code.activestate.com/recipes/578019-bytes-to-human-human-to-bytes-converter/ +SYMBOLS = { + 'customary': ('B', 'KB', 'MB', 'GB', 'T', 'P', 'E', 'Z', 'Y'), + 'customary_ext': ('byte', 'kilo', 'mega', 'giga', 'tera', 'peta', 'exa', + 'zetta', 'iotta'), + 'iec': ('Bi', 'Ki', 'Mi', 'Gi', 'Ti', 'Pi', 'Ei', 'Zi', 'Yi'), + 'iec_ext': ('byte', 'kibi', 'mebi', 'gibi', 'tebi', 'pebi', 'exbi', + 'zebi', 'yobi'), +} + + +docsdb = couch['disclosr-documents'] +out = csv.writer(open("output.csv","w"), delimiter=',',quoting=csv.QUOTE_ALL) +if __name__ == "__main__": + for doc in docsdb.view('app/datasets'): + if doc.value['url'] != "http://data.gov.au/data/" and doc.value['agencyID'] != "qld": + # Collect the package metadata. + pkg_name = filter(lambda x: x in '0123456789abcdefghijklmnopqrstuvwxyz-_', + doc.value['url'].replace("http://data.gov.au/dataset/", '').replace('/', '')[:100]); + if 'Download' in doc.value['metadata'].keys() and len(doc.value['metadata']['Download']) > 0: + for resource in doc.value['metadata']['Download']: + # http://docs.ckan.org/en/ckan-1.7/domain-model-resource.html + # (KML/KMZ) / (Shapefile) /(Other) + format = "plain" + if resource['format'] == '(XML)': + format = 'xml' + if resource['format'] == '(CSV/XLS)': + format = 'csv' + if resource['format'] == '(Shapefile)': + format = 'shp' + if resource['format'] == '(KML/KMZ)': + format = 'kml' + name = resource['href'] + if 'name' in resource.keys(): + name = resource['name'] + if resource['href'].startswith("ftp"): + out.writerow([pkg_name, url_fix(resource['href']), name,format, "ftp", ""]) + else: + try: + h = httplib2.Http(disable_ssl_certificate_validation=True) + resp = h.request(url_fix(resource['href']), 'HEAD') + content_type = resp[0]['content-type'] if 'content-type' in resp[0].keys() else "" + out.writerow([pkg_name, url_fix(resource['href']), name,format, resp[0]['status'], content_type]) + except httplib2.ServerNotFoundError: + out.writerow([pkg_name, url_fix(resource['href']), name,format, "500","badurl"]) + else: + out.writerow([pkg_name]) + --- a/documents/datagov.py +++ b/documents/datagov.py @@ -39,7 +39,9 @@ link = item.find("a") format = item.find(property="dc:format") linkobj = {"href":link['href'].replace("/bye?","").strip(), - "format": format.string.strip(), "size": format.next_sibling.string.strip()} + "format": format.string.strip()} + if format.next_sibling.string != None: + linkobj["size"] = format.next_sibling.string.strip() if link.string != None: linkobj["name"] = link.string.strip() doc['metadata'][last_title].append(linkobj) --- a/documents/genericScrapers.py +++ b/documents/genericScrapers.py @@ -72,7 +72,8 @@ edate = date.today().strftime("%Y-%m-%d") doc = {'_id': dochash, 'agencyID': self.getAgencyID() , 'url': self.getURL(), 'docID': dochash, - "date": edate, "title": "Disclosure Log Updated", "description": self.remove_control_chars(description), "diff": diff} + "date": edate, "title": "Disclosure Log Updated", + "description": self.remove_control_chars(description), "diff": self.remove_control_chars(diff)} foidocsdb.save(doc) else: print "already saved" @@ -199,11 +200,16 @@ return table.find_all('tr') def getDate(self, content, entry, doc): - date = ''.join(content.stripped_strings).strip() - (a, b, c) = date.partition("(") - date = self.remove_control_chars(a.replace("Octber", "October").replace("1012","2012").replace("Janurary","January")) - print date - edate = parse(date, dayfirst=True, fuzzy=True).strftime("%Y-%m-%d") + strdate = ''.join(content.stripped_strings).strip() + (a, b, c) = strdate.partition("(") + strdate = self.remove_control_chars(a.replace("Octber", "October").replace("1012","2012")replace("Janrurary", "January").replace("1012","2012")) + print strdate + try: + edate = parse(strdate, dayfirst=True, fuzzy=True).strftime("%Y-%m-%d") + except ValueError: + print >> sys.stderr, "ERROR date invalid %s " % strdate + print >> sys.stderr, "ERROR date originally %s " % ''.join(content.stripped_strings).strip() + edate = date.today().strftime("%Y-%m-%d") print edate doc.update({'date': edate}) return @@ -266,8 +272,7 @@ 'Summary of FOIrequest received by agency/minister', 'Summary of FOI request received', 'Description of FOI Request', "FOI request", 'Results 1 to 67 of 67'] - if doc['title'] not in badtitles\ - and doc['description'] != '': + if doc['title'] not in badtitles and 'description' in doc.keys() and doc['description'] != '': print "saving" foidocsdb.save(doc) else: @@ -277,6 +282,6 @@ print "header row" else: - print "ERROR number of columns incorrect" + print >> sys.stderr, "ERROR number of columns incorrect" print row --- a/documents/runScrapers.sh +++ b/documents/runScrapers.sh @@ -1,13 +1,21 @@ -rm /tmp/disclosr-error +DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )" +cd $DIR +echo "" > /tmp/disclosr-error for f in scrapers/*.py; do echo "Processing $f file.."; - python $f 2>/tmp/disclosr-error; + md5=`md5sum /tmp/disclosr-error` + python $f 3>&1 1>&2 2>&3 | tee --append /tmp/disclosr-error; + md52=`md5sum /tmp/disclosr-error` + if [ "$md5" != "$md52" ]; then + echo "^^^^^^^^^^^^^^ $f" >> /tmp/disclosr-error; + fi if [ "$?" -ne "0" ]; then echo "error"; - sleep 2; + sleep 1; fi done if [ -s /tmp/disclosr-error ] ; then + echo "emailling logs.."; mail -E -s "Disclosr errors" maxious@lambdacomplex.org < /tmp/disclosr-error ; fi --- a/documents/scrape.py +++ b/documents/scrape.py @@ -7,6 +7,7 @@ from urlparse import urljoin import time import os +import sys import mimetypes import urllib import urlparse @@ -89,7 +90,7 @@ def getLastAttachment(docsdb, url): hash = mkhash(url) doc = docsdb.get(hash) - if doc != None: + if doc != None and "_attachments" in doc.keys(): last_attachment_fname = doc["_attachments"].keys()[-1] last_attachment = docsdb.get_attachment(doc, last_attachment_fname) return last_attachment @@ -103,7 +104,7 @@ req = urllib2.Request(url) print "Fetching %s (%s)" % (url, hash) if url.startswith("mailto") or url.startswith("javascript") or url.startswith("#") or url == None or url == "": - print "Not a valid HTTP url" + print >> sys.stderr, "Not a valid HTTP url" return (None, None, None) doc = docsdb.get(hash) if doc == None: @@ -111,10 +112,15 @@ else: if (('page_scraped' in doc) and ((time.time() - doc['page_scraped']) < 60 * 24 * 14) or (scrape_again == False)): print "Uh oh, trying to scrape URL again too soon!" + hash - last_attachment_fname = doc["_attachments"].keys()[-1] - last_attachment = docsdb.get_attachment(doc, last_attachment_fname) - content = last_attachment - return (doc['url'], doc['mime_type'], content.read()) + if "_attachments" in doc.keys(): + last_attachment_fname = doc["_attachments"].keys()[-1] + last_attachment = docsdb.get_attachment(doc, last_attachment_fname) + content = last_attachment.read() + mime_type = doc['mime_type'] + else: + content = None + mime_type = None + return (doc['url'], mime_type, content) req.add_header("User-Agent", "Mozilla/4.0 (compatible; Prometheus webspider; owner maxious@lambdacomplex.org)") #if there is a previous version stored in couchdb, load caching helper tags @@ -159,13 +165,13 @@ #store as attachment epoch-filename except (urllib2.URLError, socket.timeout) as e: - print "error!" + print >> sys.stderr,"error!" error = "" if hasattr(e, 'reason'): error = "error %s in downloading %s" % (str(e.reason), url) elif hasattr(e, 'code'): error = "error %s in downloading %s" % (e.code, url) - print error + print >> sys.stderr, error doc['error'] = error docsdb.save(doc) return (None, None, None) --- a/documents/scrapers/0049d35216493c545ef5f7f000e6b252.py +++ b/documents/scrapers/0049d35216493c545ef5f7f000e6b252.py @@ -42,7 +42,6 @@ 'data': {'request': '', 'session': '', 'more': ''} } - - amonpy.exception(data) + #amonpy.exception(data) pass --- a/documents/scrapers/227cb6eb7d2c9f8a6e846df7447d6caa.py +++ b/documents/scrapers/227cb6eb7d2c9f8a6e846df7447d6caa.py @@ -18,13 +18,13 @@ 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(htcontent) - for row in soup.find(class_ = "ms-rteTable-GreyAlternating").find_all('tr'): + rowtitle = soup.find(class_ = "wc-title").find("h1").string + if rowtitle != None: + description = rowtitle + ": " + for row in soup.find(class_ ="wc-content").find_all('td'): if row != None: - rowtitle = row.find('th').string - if rowtitle != None: - description = description + "\n" + rowtitle + ": " - for text in row.find('td').stripped_strings: - description = description + text + for text in row.stripped_strings: + description = description + text + "\n" for atag in row.find_all("a"): if atag.has_key('href'): links.append(scrape.fullurl(link,atag['href'])) @@ -37,7 +37,7 @@ def getColumnCount(self): return 2 def getTable(self,soup): - return soup.find(class_ = "ms-rteTable-GreyAlternating") + return soup.find(class_ = "ms-rteTable-default") def getColumns(self,columns): (date, title) = columns return (title, date, title, title, None) --- a/documents/scrapers/24bd71114d3975ed9a63ad29624c62c9.py +++ b/documents/scrapers/24bd71114d3975ed9a63ad29624c62c9.py @@ -7,7 +7,7 @@ #http://www.doughellmann.com/PyMOTW/abc/ class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): def getTable(self,soup): - return soup.find(id = "inner_content") + return soup.find(class_="tborder") def getColumnCount(self): return 2 def getColumns(self,columns): --- a/documents/scrapers/3d5871a44abbbc81ef5b3a420070755d.py +++ b/documents/scrapers/3d5871a44abbbc81ef5b3a420070755d.py @@ -8,40 +8,14 @@ from datetime import * #http://www.doughellmann.com/PyMOTW/abc/ -class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): - def getTable(self,soup): - return soup.find(class_ = "inner-column").table - def getRows(self,table): - return table.tbody.find_all('tr',recursive=False) +class ScraperImplementation(genericScrapers.GenericHTMLDisclogScraper): def getColumnCount(self): - return 3 - 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 + return 0 if __name__ == '__main__': - print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) - print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) +#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 + print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericHTMLDisclogScraper) + print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericHTMLDisclogScraper) ScraperImplementation().doScrape() --- a/documents/scrapers/6fa04af95fbe7de96daa2c7560e0aad3.py +++ b/documents/scrapers/6fa04af95fbe7de96daa2c7560e0aad3.py @@ -6,8 +6,6 @@ #http://www.doughellmann.com/PyMOTW/abc/ class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): - def getTable(self,soup): - return soup.find(id = "content_div_50269").table def getColumns(self,columns): (id, date, title, description, notes) = columns return (id, date, title, description, notes) --- a/documents/scrapers/7c6adc1d41cf029bf1a0959e5156477a.py +++ b/documents/scrapers/7c6adc1d41cf029bf1a0959e5156477a.py @@ -21,11 +21,15 @@ d.make_links_absolute(base_url = self.getURL()) for table in d('table').items(): 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()) links = table('a').map(lambda i, e: pq(e).attr('href')) description = descA+" "+descB - edate = parse(idate[:12], dayfirst=True, fuzzy=True).strftime("%Y-%m-%d") + try: + edate = parse(idate[:12], dayfirst=True, fuzzy=True).strftime("%Y-%m-%d") + except ValueError: + edate = date.today().strftime("%Y-%m-%d") + pass print edate dochash = scrape.mkhash(self.remove_control_chars(title)) doc = foidocsdb.get(dochash) --- a/documents/scrapers/8e874a2fde8aa0ccdc6d14573d766540.py +++ b/documents/scrapers/8e874a2fde8aa0ccdc6d14573d766540.py @@ -18,10 +18,10 @@ 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(htcontent) - for text in soup.find(id="divFullWidthColumn").stripped_strings: + for text in soup.find(class_ = "mainContent").stripped_strings: description = description + text.encode('ascii', 'ignore') - for atag in soup.find(id="divFullWidthColumn").find_all("a"): + for atag in soup.find(id="SortingTable").find_all("a"): if atag.has_key('href'): links.append(scrape.fullurl(link,atag['href'])) --- a/documents/scrapers/a687a9eaab9e10e9e118d3fd7cf0e13a.py +++ b/documents/scrapers/a687a9eaab9e10e9e118d3fd7cf0e13a.py @@ -7,11 +7,11 @@ #http://www.doughellmann.com/PyMOTW/abc/ class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): def getTable(self,soup): - return soup.find(id="ctl00_ContentPlaceHolderMainNoAjax_EdtrTD1494_2").table + return soup.find(id="int-content").table def getColumnCount(self): - return 4 + return 3 def getColumns(self,columns): - (blank,id, title,date) = columns + (id, title,date) = columns return (id, date, title, title, None) if __name__ == '__main__': --- /dev/null +++ b/documents/scrapers/b0ca7fddcd1c965787daea47f2d32e0a.py @@ -1,1 +1,17 @@ +import sys,os +sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) +import genericScrapers +import scrape +from bs4 import BeautifulSoup +#http://www.doughellmann.com/PyMOTW/abc/ +class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): + def getColumns(self,columns): + (id, date, title, description, notes) = columns + return (id, date, title, description, notes) + +if __name__ == '__main__': + print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) + print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) + ScraperImplementation().doScrape() + --- a/documents/scrapers/dfd7414bb0c21a0076ab559901ae0588.py +++ b/documents/scrapers/dfd7414bb0c21a0076ab559901ae0588.py @@ -10,7 +10,7 @@ (id, date, title, description, notes) = columns return (id, date, title, description, notes) def getTable(self,soup): - return soup.find(class_ = "content") + return soup.find(class_ = "simpletable") if __name__ == '__main__': print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) --- a/documents/scrapers/f2ab2908d8ee56ed8d995ef4187e75e6.py +++ b/documents/scrapers/f2ab2908d8ee56ed8d995ef4187e75e6.py @@ -10,7 +10,7 @@ (id, date, title, description, notes) = columns return (id, date, title, description, notes) def getTable(self,soup): - return soup.find(id = "content").table + return soup.find("table") if __name__ == '__main__': print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)