BackTrackZ/scrapy
BackTrackZ/scrapy
1
0
Fork 0
mirror of https://github.com/scrapy/scrapy.git synced 2025-02-26 20:23:53 +00:00
Code Releases Wiki Activity

SitemapSpider: added support for parsing gzipped sitemaps (patch contributed by Rolando Espinoza)

Browse Source
This commit is contained in:
Pablo Hoffman 2011-07-06 01:33:46 -03:00
parent 5707051352
commit 949e11ee31
1 changed files with 11 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
scrapy/contrib/spiders/sitemap.py
View File

@ -3,6 +3,7 @@ import re
from scrapy.spider import BaseSpider from scrapy.spider import BaseSpider
from scrapy.http import Request, XmlResponse from scrapy.http import Request, XmlResponse
from scrapy.utils.sitemap import Sitemap, sitemap_urls_from_robots from scrapy.utils.sitemap import Sitemap, sitemap_urls_from_robots
from scrapy.utils.gz import gunzip
from scrapy import log from scrapy import log
class SitemapSpider(BaseSpider): class SitemapSpider(BaseSpider):
@ -28,10 +29,15 @@ class SitemapSpider(BaseSpider):
for url in sitemap_urls_from_robots(response.body): for url in sitemap_urls_from_robots(response.body):
yield Request(url, callback=self._parse_sitemap) yield Request(url, callback=self._parse_sitemap)
else: else:
if not isinstance(response, XmlResponse): if isinstance(response, XmlResponse):
body = response.body
elif is_gzipped(response):
body = gunzip(response.body)
else:
log.msg("Ignoring non-XML sitemap: %s" % response, log.WARNING) log.msg("Ignoring non-XML sitemap: %s" % response, log.WARNING)
return return
s = Sitemap(response.body)
s = Sitemap(body)
if s.type == 'sitemapindex': if s.type == 'sitemapindex':
for loc in iterloc(s): for loc in iterloc(s):
if any(x.search(loc) for x in self._follow): if any(x.search(loc) for x in self._follow):
@ -43,6 +49,9 @@ class SitemapSpider(BaseSpider):
yield Request(loc, callback=c) yield Request(loc, callback=c)
break break
def is_gzipped(response):
ctype = response.headers.get('Content-Type', '')
return ctype in ('application/x-gzip', 'applicatoin/gzip')
def regex(x): def regex(x):
if isinstance(x, basestring): if isinstance(x, basestring):