RomanNum3ral
/
scrapy
mirror of https://github.com/scrapy/scrapy.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge branch '0.14'

This commit is contained in:
Daniel Graña 2011-12-14 13:09:00 -02:00
parent 9b84914736 63d583d9be
commit aea060e144
2 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
docs/intro/tutorial.rst
View File

@ -268,19 +268,19 @@ The shell also instantiates two selectors, one for HTML (in the ``hxs``
variable) and one for XML (in the ``xxs`` variable) with this response. So let's
try them::
In [1]: hxs.select('/html/head/title')
Out[1]: [<HtmlXPathSelector (title) xpath=/html/head/title>]
In [1]: hxs.select('//title')
Out[1]: [<HtmlXPathSelector (title) xpath=//title>]
In [2]: hxs.select('/html/head/title').extract()
In [2]: hxs.select('//title').extract()
Out[2]: [u'<title>Open Directory - Computers: Programming: Languages: Python: Books</title>']
In [3]: hxs.select('/html/head/title/text()')
Out[3]: [<HtmlXPathSelector (text) xpath=/html/head/title/text()>]
In [3]: hxs.select('//title/text()')
Out[3]: [<HtmlXPathSelector (text) xpath=//title/text()>]
In [4]: hxs.select('/html/head/title/text()').extract()
In [4]: hxs.select('//title/text()').extract()
Out[4]: [u'Open Directory - Computers: Programming: Languages: Python: Books']
In [5]: hxs.select('/html/head/title/text()').re('(\w+):')
In [5]: hxs.select('//title/text()').re('(\w+):')
Out[5]: [u'Computers', u'Programming', u'Languages', u'Python']
Extracting the data

2
scrapy/contrib/pipeline/images.py
View File

@ -102,7 +102,7 @@ class S3ImagesStore(object):
def _get_boto_bucket(self):
from boto.s3.connection import S3Connection
c = S3Connection(self.AWS_ACCESS_KEY_ID, self.AWS_SECRET_ACCESS_KEY)
c = S3Connection(self.AWS_ACCESS_KEY_ID, self.AWS_SECRET_ACCESS_KEY, is_secure=False)
return c.get_bucket(self.bucket, validate=False)
def _get_boto_key(self, key):