Last active
July 28, 2020 20:40
-
-
Save hendrixjoseph/29e4b9b9b61d3a4ba4bd7a80aa111764 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
package com.joehxblog; | |
import java.io.FileWriter; | |
import java.io.IOException; | |
import java.util.function.Consumer; | |
import org.jsoup.HttpStatusException; | |
import org.jsoup.Jsoup; | |
import org.jsoup.nodes.Document; | |
import org.jsoup.select.Elements; | |
public class PatentCounter { | |
public static final String URL = "https://patents.google.com/patent/US"; | |
public static void main(final String... args) { | |
try (FileWriter writer = new FileWriter("patents.csv")) { | |
writer.write("count,year,month,day" + System.lineSeparator()); | |
final int start = 1; | |
final int end = 10_709_051; | |
final int increment = 97_355; | |
// Got to use this type of for loop rather than an | |
// IntStream due to a possible thrown exception. | |
for (int i = start; i <= end; i += increment) { | |
try { | |
final Document doc = Jsoup.connect(URL + i).get(); | |
// <time itemprop="publicationDate" datetime="1836-07-13">1836-07-13</time> | |
final Elements granted = doc.getElementsByAttributeValue("itemprop", "publicationDate"); | |
write(t -> { | |
try { | |
writer.write(t); | |
} catch (final IOException e) { | |
e.printStackTrace(); | |
} | |
}, i, granted); | |
write(System.out::print, i, granted); | |
} catch (final HttpStatusException e) { | |
System.out.println("Patent " + i + " not found."); | |
} | |
} | |
} catch (final IOException e) { | |
e.printStackTrace(); | |
} | |
} | |
public static void write(final Consumer<String> writer, final int i, final Elements granted) { | |
writer.accept(i + ","); | |
writer.accept(granted.first().text().replace('-', ',')); | |
writer.accept(System.lineSeparator()); | |
} | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<project xmlns="http://maven.apache.org/POM/4.0.0" | |
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" | |
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 | |
https://maven.apache.org/xsd/maven-4.0.0.xsd"> | |
<modelVersion>4.0.0</modelVersion> | |
<groupId>com.joehxblog</groupId> | |
<artifactId>patent.counter</artifactId> | |
<version>0.0.1-SNAPSHOT</version> | |
<name>Patent Counter</name> | |
<dependencies> | |
<dependency> | |
<groupId>org.jsoup</groupId> | |
<artifactId>jsoup</artifactId> | |
<version>1.13.1</version> | |
</dependency> | |
</dependencies> | |
</project> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
This code was used for my blog post Is Technology Accelerating? An Analysis of US Patent Records.