--- a/documents/scrape.py +++ b/documents/scrape.py @@ -1,1 +1,204 @@ - +#http://packages.python.org/CouchDB/client.html +import couchdb +import urllib2 +from BeautifulSoup import BeautifulSoup +import re +import hashlib +from urlparse import urljoin +import time +import os +import mimetypes +import re +import urllib +import urlparse + +def canonurl(url): + r"""Return the canonical, ASCII-encoded form of a UTF-8 encoded URL, or '' + if the URL looks invalid. + >>> canonurl('\xe2\x9e\xa1.ws') # tinyarro.ws + 'http://xn--hgi.ws/' + """ + # strip spaces at the ends and ensure it's prefixed with 'scheme://' + url = url.strip() + if not url: + return '' + if not urlparse.urlsplit(url).scheme: + url = 'http://' + url + + # turn it into Unicode + #try: + # url = unicode(url, 'utf-8') + #except UnicodeDecodeError: + # return '' # bad UTF-8 chars in URL + + # parse the URL into its components + parsed = urlparse.urlsplit(url) + scheme, netloc, path, query, fragment = parsed + + # ensure scheme is a letter followed by letters, digits, and '+-.' chars + if not re.match(r'[a-z][-+.a-z0-9]*$', scheme, flags=re.I): + return '' + scheme = str(scheme) + + # ensure domain and port are valid, eg: sub.domain.<1-to-6-TLD-chars>[:port] + match = re.match(r'(.+\.[a-z0-9]{1,6})(:\d{1,5})?$', netloc, flags=re.I) + if not match: + return '' + domain, port = match.groups() + netloc = domain + (port if port else '') + netloc = netloc.encode('idna') + + # ensure path is valid and convert Unicode chars to %-encoded + if not path: + path = '/' # eg: 'http://google.com' -> 'http://google.com/' + path = urllib.quote(urllib.unquote(path.encode('utf-8')), safe='/;') + + # ensure query is valid + query = urllib.quote(urllib.unquote(query.encode('utf-8')), safe='=&?/') + + # ensure fragment is valid + fragment = urllib.quote(urllib.unquote(fragment.encode('utf-8'))) + + # piece it all back together, truncating it to a maximum of 4KB + url = urlparse.urlunsplit((scheme, netloc, path, query, fragment)) + return url[:4096] + +#http://diveintopython.org/http_web_services/etags.html +class NotModifiedHandler(urllib2.BaseHandler): + def http_error_304(self, req, fp, code, message, headers): + addinfourl = urllib2.addinfourl(fp, headers, req.get_full_url()) + addinfourl.code = code + return addinfourl + +def fetchURL(docsdb, url, fieldName, agencyID, scrape_again=True): + url = canonurl(url) + hash = hashlib.md5(url).hexdigest().encode("utf-8") + req = urllib2.Request(url) + print "Fetching %s" % url + if url.startswith("mailto") or url.startswith("javascript") or url.startswith("#") or url == None or url == "": + print "Not a valid HTTP url" + return (None,None,None) + doc = docsdb.get(hash) + if doc == None: + doc = {'_id': hash, 'agencyID': agencyID, 'url': url, 'fieldName':fieldName} + else: + if (('page_scraped' in doc) and (time.time() - doc['page_scraped']) < 999999): + print "Uh oh, trying to scrape URL again too soon!" + last_attachment_fname = doc["_attachments"].keys()[-1] + last_attachment = docsdb.get_attachment(doc,last_attachment_fname) + return (doc['url'],doc['mime_type'],last_attachment.read()) + if scrape_again == False: + print "Not scraping this URL again as requested" + return (None,None,None) + + time.sleep(3) # wait 3 seconds to give webserver time to recover + + 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 + if doc.has_key('etag'): + req.add_header("If-None-Match", doc['etag']) + if doc.has_key('last_modified'): + req.add_header("If-Modified-Since", doc['last_modified']) + + opener = urllib2.build_opener(NotModifiedHandler()) + try: + url_handle = opener.open(req) + doc['url'] = url_handle.geturl() # may have followed a redirect to a new url + headers = url_handle.info() # the addinfourls have the .info() too + doc['etag'] = headers.getheader("ETag") + doc['last_modified'] = headers.getheader("Last-Modified") + doc['date'] = headers.getheader("Date") + doc['page_scraped'] = time.time() + doc['web_server'] = headers.getheader("Server") + doc['via'] = headers.getheader("Via") + doc['powered_by'] = headers.getheader("X-Powered-By") + doc['file_size'] = headers.getheader("Content-Length") + content_type = headers.getheader("Content-Type") + if content_type != None: + doc['mime_type'] = content_type.split(";")[0] + else: + (type,encoding) = mimetypes.guess_type(url) + doc['mime_type'] = type + if hasattr(url_handle, 'code'): + if url_handle.code == 304: + print "the web page has not been modified" + return (None,None,None) + else: + content = url_handle.read() + docsdb.save(doc) + doc = docsdb.get(hash) # need to get a _rev + docsdb.put_attachment(doc, content, str(time.time())+"-"+os.path.basename(url), doc['mime_type']) + return (doc['url'], doc['mime_type'], content) + #store as attachment epoch-filename + except urllib2.URLError as e: + 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 + doc['error'] = error + docsdb.save(doc) + return (None,None,None) + + + +def scrapeAndStore(docsdb, url, depth, fieldName, agencyID): + (url,mime_type,content) = fetchURL(docsdb, url, fieldName, agencyID) + badURLs = ["http://www.ausport.gov.au/supporting/funding/grants_and_scholarships/grant_funding_report"] + if content != None and depth > 0 and url != "http://www.ausport.gov.au/supporting/funding/grants_and_scholarships/grant_funding_report": + 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) + navIDs = soup.findAll(id=re.compile('nav|Nav|menu|bar|left|right|sidebar|more-links|breadcrumb|footer|header')) + for nav in navIDs: + print "Removing element", nav['id'] + nav.extract() + navClasses = soup.findAll(attrs={'class' : re.compile('nav|menu|bar|left|right|sidebar|more-links|breadcrumb|footer|header')}) + for nav in navClasses: + print "Removing element", nav['class'] + nav.extract() + links = soup.findAll('a') # soup.findAll('a', id=re.compile("^p-")) + linkurls = set([]) + for link in links: + if link.has_key("href"): + if link['href'].startswith("http"): + # lets not do external links for now + # linkurls.add(link['href']) + None + if link['href'].startswith("mailto"): + # not http + None + if link['href'].startswith("javascript"): + # not http + None + else: + # remove anchors and spaces in urls + link['href'] = link['href'].replace(" ","%20") + link['href'] = re.sub('#.*$','',link['href']) + linkurls.add(urljoin(url,link['href'])) + for linkurl in linkurls: + #print linkurl + scrapeAndStore(docsdb, linkurl, depth-1, fieldName, agencyID) + +couch = couchdb.Server('http://127.0.0.1:5984/') +# select database +agencydb = couch['disclosr-agencies'] +docsdb = couch['disclosr-documents'] + +if __name__ == "__main__": + for row in agencydb.view('app/getScrapeRequired'): #not recently scraped agencies view? + agency = agencydb.get(row.id) + print agency['name'] + for key in agency.keys(): + if key == 'website': + scrapeAndStore(docsdb, agency[key],0,key,agency['_id']) + if key.endswith('URL'): + print key + depth = 1 + if 'scrapeDepth' in agency.keys(): + depth = agency['scrapeDepth'] + scrapeAndStore(docsdb, agency[key],depth,key,agency['_id']) + agency['metadata']['lastScraped'] = time.time() + agencydb.save(agency) +