demos: Update webspider demo to python 3

diff --git a/demos/webspider/webspider.py b/demos/webspider/webspider.py
index dd8e6b385bc2fa593979b7d302c66f558c871f04..0c264c00a18cd182bdda7be415ff5e64cdb872e6 100755 (executable)
--- a/demos/webspider/webspider.py
+++ b/demos/webspider/webspider.py
@@ -1,42 +1,30 @@
-#!/usr/bin/env python
+#!/usr/bin/env python3
 
 import time
 from datetime import timedelta
 
-try:
-    from HTMLParser import HTMLParser
-    from urlparse import urljoin, urldefrag
-except ImportError:
-    from html.parser import HTMLParser
-    from urllib.parse import urljoin, urldefrag
+from html.parser import HTMLParser
+from urllib.parse import urljoin, urldefrag
 
-from tornado import httpclient, gen, ioloop, queues
+from tornado import gen, httpclient, ioloop, queues
 
 base_url = 'http://www.tornadoweb.org/en/stable/'
 concurrency = 10
 
 
-@gen.coroutine
-def get_links_from_url(url):
+async def get_links_from_url(url):
     """Download the page at `url` and parse it for links.
 
     Returned links have had the fragment after `#` removed, and have been made
     absolute so, e.g. the URL 'gen.html#tornado.gen.coroutine' becomes
     'http://www.tornadoweb.org/en/stable/gen.html'.
     """
-    try:
-        response = yield httpclient.AsyncHTTPClient().fetch(url)
-        print('fetched %s' % url)
+    response = await httpclient.AsyncHTTPClient().fetch(url)
+    print('fetched %s' % url)
 
-        html = response.body if isinstance(response.body, str) \
-            else response.body.decode(errors='ignore')
-        urls = [urljoin(url, remove_fragment(new_url))
-                for new_url in get_links(html)]
-    except Exception as e:
-        print('Exception: %s %s' % (e, url))
-        raise gen.Return([])
-
-    raise gen.Return(urls)
+    html = response.body.decode(errors='ignore')
+    return [urljoin(url, remove_fragment(new_url))
+            for new_url in get_links(html)]
 
 
 def remove_fragment(url):
@@ -60,47 +48,50 @@ def get_links(html):
     return url_seeker.urls
 
 
-@gen.coroutine
-def main():
+async def main():
     q = queues.Queue()
     start = time.time()
     fetching, fetched = set(), set()
 
-    @gen.coroutine
-    def fetch_url():
-        current_url = yield q.get()
-        try:
-            if current_url in fetching:
-                return
-
-            print('fetching %s' % current_url)
-            fetching.add(current_url)
-            urls = yield get_links_from_url(current_url)
-            fetched.add(current_url)
+    async def fetch_url(current_url):
+        if current_url in fetching:
+            return
 
-            for new_url in urls:
-                # Only follow links beneath the base URL
-                if new_url.startswith(base_url):
-                    yield q.put(new_url)
+        print('fetching %s' % current_url)
+        fetching.add(current_url)
+        urls = await get_links_from_url(current_url)
+        fetched.add(current_url)
 
-        finally:
-            q.task_done()
+        for new_url in urls:
+            # Only follow links beneath the base URL
+            if new_url.startswith(base_url):
+                await q.put(new_url)
 
-    @gen.coroutine
-    def worker():
-        while True:
-            yield fetch_url()
+    async def worker():
+        async for url in q:
+            if url is None:
+                return
+            try:
+                await fetch_url(url)
+            except Exception as e:
+                print('Exception: %s %s' % (e, url))
+            finally:
+                q.task_done()
 
-    q.put(base_url)
+    await q.put(base_url)
 
     # Start workers, then wait for the work queue to be empty.
-    for _ in range(concurrency):
-        worker()
-    yield q.join(timeout=timedelta(seconds=300))
+    workers = gen.multi([worker() for _ in range(concurrency)])
+    await q.join(timeout=timedelta(seconds=300))
     assert fetching == fetched
     print('Done in %d seconds, fetched %s URLs.' % (
         time.time() - start, len(fetched)))
 
+    # Signal all the workers to exit.
+    for _ in range(concurrency):
+        await q.put(None)
+    await workers
+
 
 if __name__ == '__main__':
     io_loop = ioloop.IOLoop.current()