Closed cwd24 closed 6 years ago
Tested with the following local change, to reduce redirects when run from the UK:
diff --git a/Lib/corpuscrawler/util.py b/Lib/corpuscrawler/util.py index f22e6b9..e6b294c 100644 --- a/Lib/corpuscrawler/util.py +++ b/Lib/corpuscrawler/util.py @@ -316,7 +316,7 @@ class Crawler(object):
def crawl_bbc_news(crawler, out, urlprefix):
Thank you!
Tested with the following local change, to reduce redirects when run from the UK:
diff --git a/Lib/corpuscrawler/util.py b/Lib/corpuscrawler/util.py index f22e6b9..e6b294c 100644 --- a/Lib/corpuscrawler/util.py +++ b/Lib/corpuscrawler/util.py @@ -316,7 +316,7 @@ class Crawler(object):
using the same site structure for all languages.
def crawl_bbc_news(crawler, out, urlprefix):
sitemap = {'http://www.bbc.com/burmese/world-41146701': None}