From cbd135223ddcb4b93296a5b570ad6926e404b82c Mon Sep 17 00:00:00 2001 From: Kamo Petrosyan Date: Mon, 17 Feb 2020 03:34:07 +0300 Subject: [PATCH] readme fixed --- README.md | 63 ++++++++++++++++++++++--------------------------------- 1 file changed, 25 insertions(+), 38 deletions(-) diff --git a/README.md b/README.md index d691d75..28bb622 100644 --- a/README.md +++ b/README.md @@ -1,38 +1,25 @@ -# pysitemap -Sitemap generator - -## installing - - pip install sitemap-generator - -## Gevent - -Sitemap-generator uses [gevent](http://www.gevent.org/) to implement multiprocessing. Install gevent: - - pip install gevent - -## example - - import pysitemap - - - if __name__ == '__main__': - url = 'http://www.example.com/' # url from to crawl - logfile = 'errlog.log' # path to logfile - oformat = 'xml' # output format - crawl = pysitemap.Crawler(url=url, logfile=logfile, oformat=oformat) - crawl.crawl() - - -## multiprocessing example - - - import pysitemap - - - if __name__ == '__main__': - url = 'http://www.example.com/' # url from to crawl - logfile = 'errlog.log' # path to logfile - oformat = 'xml' # output format - crawl = pysitemap.Crawler(url=url, logfile=logfile, oformat=oformat) - crawl.crawl(pool_size=10) # 10 parsing processes +# pysitemap +Sitemap generator + +## installing + + pip install sitemap-generator + +## example + + import sys + import logging + from pysitemap import crawler + + if __name__ == '__main__': + if '--iocp' in sys.argv: + from asyncio import events, windows_events + sys.argv.remove('--iocp') + logging.info('using iocp') + el = windows_events.ProactorEventLoop() + events.set_event_loop(el) + + # root_url = sys.argv[1] + root_url = 'https://www.haikson.com' + crawler(root_url, out_file='sitemap.xml') +