Fixing Google Patents.
This commit is contained in:
Matt Burton
parent
70ebccc827
commit
f303db22e7
1 changed files with 60 additions and 71 deletions
|
|
@ -12,8 +12,12 @@
|
|||
}
|
||||
|
||||
function detectWeb(doc, url) {
|
||||
var namespace = doc.documentElement.namespaceURI;
|
||||
var nsResolver = namespace ? function(prefix) {
|
||||
if (prefix == 'x') return namespace; else return null;
|
||||
} : null;
|
||||
|
||||
if (doc.location.href.match("Search")) {
|
||||
if (doc.evaluate('//font[contains(./text(), "Result")]', doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext()) {
|
||||
return "multiple";
|
||||
} else if (doc.location.href.match("id")) {
|
||||
return "patent";
|
||||
|
|
@ -36,44 +40,28 @@ function scrape(doc, url) {
|
|||
} : null;
|
||||
|
||||
var dataTags = new Object();
|
||||
var headings = new Array();
|
||||
var newItem = new Zotero.Item("patent");
|
||||
|
||||
//checks format type
|
||||
if (doc.location.href.match("printsec")) {
|
||||
|
||||
var contents = doc.evaluate('//table[@id="summarytable"]/tbody/tr[1]/td', doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().textContent;
|
||||
var xPathHeadings = doc.evaluate('//b', doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||||
|
||||
var xPathCount = doc.evaluate('count (//b)', doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||||
|
||||
if (doc.evaluate('//span[@class="addmd"]', doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext()) {
|
||||
|
||||
var author = doc.evaluate('//span[@class="addmd"]', doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().textContent;
|
||||
newItem.creators.push(Zotero.Utilities.cleanAuthor(author, "inventor"));
|
||||
//Grab the patent_bibdata items and the text node directly next to them
|
||||
var xPathHeadings = doc.evaluate('//div[@class="patent_bibdata"]//b', doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||||
var xPathContents = doc.evaluate('//div[@class="patent_bibdata"]//b/following::text()[1]', doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||||
|
||||
// create an associative array of the items and their contents
|
||||
var heading, content;
|
||||
while( heading = xPathHeadings.iterateNext(), content = xPathContents.iterateNext()){
|
||||
if(heading.textContent == 'Publication number'){
|
||||
content = doc.evaluate('//div[@class="patent_bibdata"]//b[text()="Publication number"]/following::nobr[1]', doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
|
||||
}
|
||||
|
||||
} else {
|
||||
|
||||
var xPathHeadings = doc.evaluate('//div[@class="patent_bibdata"]/p/b', doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||||
|
||||
var xPathCount = doc.evaluate('count (//div[@class="patent_bibdata"]/p/b)', doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||||
|
||||
|
||||
var xPathContents = doc.evaluate('//div[@class="patent_bibdata"]/p', doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||||
var contentsCount = doc.evaluate('count (//div[@class="patent_bibdata"]/p)', doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||||
|
||||
var contents;
|
||||
for (i = 0; i < contentsCount.numberValue; i++) {
|
||||
contents = (contents + xPathContents.iterateNext().textContent + " ");
|
||||
}
|
||||
|
||||
if (doc.evaluate('//td[3]/p', doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext()) {
|
||||
newItem.abstractNote = (doc.evaluate('//td[3]/p', doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().textContent.replace("Abstract", ''));
|
||||
}
|
||||
|
||||
dataTags[heading.textContent] = content.textContent.replace(": ", '');;
|
||||
//Zotero.debug(dataTags);
|
||||
}
|
||||
|
||||
if (doc.evaluate('//td[3]/p', doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext()) {
|
||||
newItem.abstractNote = (doc.evaluate('//td[3]/p', doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().textContent.replace("Abstract", ''));
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
for (var i =0; i < xPathCount.numberValue; i++) {
|
||||
|
||||
headings.push(xPathHeadings.iterateNext().textContent);
|
||||
|
|
@ -83,23 +71,28 @@ function scrape(doc, url) {
|
|||
|
||||
var splitContent = new Array();
|
||||
splitContent = contents.split(/xxx/);
|
||||
|
||||
*/
|
||||
//associate headings with contents.
|
||||
for (var i = 0; i < headings.length; i++) {
|
||||
fieldTitle = headings[i].replace(/\s+|\W*/g, '');
|
||||
|
||||
if (fieldTitle == "USClassification" | fieldTitle == "InternationalClassification" | fieldTitle == "Abstract") {
|
||||
|
||||
//extra field\
|
||||
newItem.extra = '';
|
||||
|
||||
for (fieldTitle in dataTags) {
|
||||
Zotero.debug(fieldTitle);
|
||||
//fieldTitle = item.replace(/\s+|\W*/g, '');
|
||||
/*
|
||||
if (fieldTitle == "US Classification" | fieldTitle == "International Classification" | fieldTitle == "Abstract") {
|
||||
dataTags[fieldTitle] = splitContent[i+1];
|
||||
} else {
|
||||
dataTags[fieldTitle] = splitContent[i+1].replace(": ", '');
|
||||
}
|
||||
|
||||
*/
|
||||
if (dataTags[fieldTitle].match("About this patent")) {
|
||||
dataTags[fieldTitle] = dataTags[fieldTitle].replace("About this patent", '');
|
||||
}
|
||||
|
||||
//author(s)
|
||||
if (fieldTitle == "Inventors") {
|
||||
if (fieldTitle == "Inventors" | fieldTitle == "Inventor") {
|
||||
var authors = dataTags[fieldTitle].split(", ");
|
||||
for (var j = 0; j < authors.length; j++) {
|
||||
newItem.creators.push(Zotero.Utilities.cleanAuthor(authors[j], "inventor"));
|
||||
|
|
@ -107,26 +100,28 @@ function scrape(doc, url) {
|
|||
} else if (fieldTitle == "Inventor") {
|
||||
newItem.creators.push(Zotero.Utilities.cleanAuthor(dataTags["Inventor"], "inventor"));
|
||||
}
|
||||
|
||||
if (fieldTitle == "U.S. Classification" ) {
|
||||
newItem.extra += "U.S. Classification: " + dataTags["U.S. Classification"]+"\n";
|
||||
} else if (fieldTitle == "International Classification" ) {
|
||||
newItem.extra += "International Classification: " + dataTags["International Classification"]+"\n";
|
||||
} else if (fieldTitle == "Filing date" ) {
|
||||
newItem.extra += "Filing Date: " + dataTags["Filing date"]+"\n";
|
||||
} else if (fieldTitle == "Publication number" ) {
|
||||
newItem.extra += "Publication number: " +dataTags["Publication number"]+"\n";
|
||||
}
|
||||
}
|
||||
|
||||
//extra field
|
||||
if (dataTags["USClassification"] && dataTags["InternationalClassification"]) {
|
||||
Zotero.debug(doc.title);
|
||||
newItem.extra = ("U.S. Classification: " + dataTags["USClassification"] + "; International Classification: " + dataTags["InternationalClassification"]);
|
||||
} else if (dataTags["USClassification"] ) {
|
||||
newItem.extra = ("U.S. Classification: " + dataTags["USClassification"]);
|
||||
} else if (dataTags["InternationalClassification"]) {
|
||||
newItem.extra = ("International Classification: " + dataTags["InternationalClassification"]);
|
||||
}
|
||||
|
||||
|
||||
associateData (newItem, dataTags, "Patentnumber", "patentNumber");
|
||||
associateData (newItem, dataTags, "Issuedate", "date");
|
||||
associateData (newItem, dataTags, "Patent number", "patentNumber");
|
||||
associateData (newItem, dataTags, "Issue date", "date");
|
||||
associateData (newItem, dataTags, "Assignees", "assignee");
|
||||
associateData (newItem, dataTags, "Assignee", "assignee");
|
||||
associateData (newItem, dataTags, "Abstract", "abstractNote");
|
||||
associateData (newItem, dataTags, "Applicationnumber", "applicationNumber");
|
||||
associateData (newItem, dataTags, "Application number", "applicationNumber");
|
||||
|
||||
newItem.title = doc.evaluate('//h2[@class="title"]', doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().textContent;
|
||||
newItem.title = doc.evaluate('//h1[@class="title"]', doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().textContent;
|
||||
newItem.url = doc.location.href;
|
||||
|
||||
newItem.complete();
|
||||
|
|
@ -138,33 +133,27 @@ function doWeb(doc, url) {
|
|||
if (prefix == 'x') return namespace; else return null;
|
||||
} : null;
|
||||
|
||||
var host = 'http://' + doc.location.host + "/";
|
||||
|
||||
var articles = new Array();
|
||||
|
||||
if (detectWeb(doc, url) == "multiple") {
|
||||
var iterator = doc.evaluate('//a[@class = "big"]', doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||||
var links = [];
|
||||
var element = iterator.iterateNext();
|
||||
var items = new Object();
|
||||
|
||||
var xPathFirstTitle = doc.evaluate('//div[@id="results_container"]/a', doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||||
var firstTitle = xPathFirstTitle.iterateNext();
|
||||
|
||||
var titles = doc.evaluate('//p/a', doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||||
|
||||
items[firstTitle.href] = firstTitle.textContent;
|
||||
|
||||
var next_title;
|
||||
while (next_title = titles.iterateNext()) {
|
||||
if (next_title.textContent.match("RSS feed")) {
|
||||
|
||||
} else {
|
||||
items[next_title.href] = next_title.textContent;
|
||||
}
|
||||
while(element) {
|
||||
items[element.href] = element.textContent;
|
||||
element = iterator.iterateNext();
|
||||
}
|
||||
items = Zotero.selectItems(items);
|
||||
if(!items) return true;
|
||||
for (var i in items) {
|
||||
articles.push(i);
|
||||
}
|
||||
} else {
|
||||
articles = [url];
|
||||
|
||||
}
|
||||
Zotero.Utilities.processDocuments(articles, scrape, function() {Zotero.done();});
|
||||
Zotero.wait();
|
||||
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in a new issue