From c6b33542398c933a6272586e6280f7026b63a124 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Wed, 19 Aug 2020 23:00:34 -0700 Subject: update robots.txt and sitemap.xml - show minimal robots/sitemap if not in prod environment - default to allow all in robots.txt; link to sitemap index files - basic sitemap.xml without entity-level links --- python/fatcat_web/routes.py | 15 +++++++++++++-- python/fatcat_web/static/robots.deny_all.txt | 7 +++++++ python/fatcat_web/static/robots.txt | 19 +++++++++++++++++++ python/fatcat_web/static/sitemap.xml | 13 +++++++++++++ 4 files changed, 52 insertions(+), 2 deletions(-) create mode 100644 python/fatcat_web/static/robots.deny_all.txt create mode 100644 python/fatcat_web/static/sitemap.xml diff --git a/python/fatcat_web/routes.py b/python/fatcat_web/routes.py index da2bb6cf..c66c7f0c 100644 --- a/python/fatcat_web/routes.py +++ b/python/fatcat_web/routes.py @@ -1157,7 +1157,18 @@ def page_rfc(): return render_template('rfc.html') @app.route('/robots.txt', methods=['GET']) -def robots(): +def page_robots_txt(): + if conf.FATCAT_DOMAIN == "fatcat.wiki": + robots_path = "robots.txt" + else: + robots_path = "robots.deny_all.txt" return send_from_directory(os.path.join(app.root_path, 'static'), - 'robots.txt', + robots_path, mimetype='text/plain') + +@app.route('/sitemap.xml', methods=['GET']) +def page_sitemap_xml(): + if conf.FATCAT_DOMAIN == "fatcat.wiki": + return redirect('/sitemaps/sitemap.xml') + else: + abort(404) diff --git a/python/fatcat_web/static/robots.deny_all.txt b/python/fatcat_web/static/robots.deny_all.txt new file mode 100644 index 00000000..b88274b1 --- /dev/null +++ b/python/fatcat_web/static/robots.deny_all.txt @@ -0,0 +1,7 @@ +# Hello friends! + +# You have found a QA/development instance of the Fatcat catalog. The canonical +# location is https://fatcat.wiki, please crawl and index that location instead. + +User-agent: * +Disallow: / diff --git a/python/fatcat_web/static/robots.txt b/python/fatcat_web/static/robots.txt index a168f11b..e89af36e 100644 --- a/python/fatcat_web/static/robots.txt +++ b/python/fatcat_web/static/robots.txt @@ -1 +1,20 @@ # Hello friends! +# If you are considering large or automated crawling, you may want to look at +# our API (https://api.fatcat.wiki) or bulk database snapshots instead. + +# by default, can crawl anything on this domain. HTTP 429 ("backoff") status +# codes are used for rate-limiting instead of any crawl delay specified here. +# Up to a handful concurrent requests should be fine. +User-agent: * +Allow: / + +# crawling search result pages is expensive, so we do specify a long crawl delay for those +User-agent: * +Allow: /release/search +Allow: /container/search +Allow: /coverage/search +Crawl-delay: 5 + +Sitemap: https://fatcat.wiki/sitemap.xml +Sitemap: https://fatcat.wiki/sitemap-index-releases.xml +Sitemap: https://fatcat.wiki/sitemap-index-containers.xml diff --git a/python/fatcat_web/static/sitemap.xml b/python/fatcat_web/static/sitemap.xml new file mode 100644 index 00000000..e6189aa4 --- /dev/null +++ b/python/fatcat_web/static/sitemap.xml @@ -0,0 +1,13 @@ + + + + https://fatcat.wiki/ + https://fatcat.wiki/about + https://fatcat.wiki/rfc + https://fatcat.wiki/stats + https://fatcat.wiki/changelog + https://fatcat.wiki/release/lookup + https://fatcat.wiki/container/lookup + https://fatcat.wiki/file/lookup + + -- cgit v1.2.3