SCRAPY配置

1  yum groupinstall "Development tools"

2  yum install zlib-devel bzip2-devel openssl-devel ncurses-devel sqlite-devel

       wget https://www.python.org/ftp/python/2.7.11/Python-2.7.11.tgz
       tar vxf Python-2.7.11.tgz

6  cd Python-2.7.11

8  ./configure --prefix=/usr/local

9  make && make install

10  python -V

      wget  https://bootstrap.pypa.io/get-pip.py --no-check-certificate

11  python get-pip.py

    wget https://pypi.python.org/packages/ff/d4/209f4939c49e31f5524fa0027bf1c8ec3107abaf7c61fdaad704a648c281/setuptools-21.0.0.tar.gz#md5=81964fdb89534118707742e6d1a1ddb4 --no-check-certificate

21  tar zxvf setuptools-21.0.0.tar.gz

23  cd setuptools-21.0.0

24  python setup.py install

25  pip install scrapy

26  cat > myspider.py <<EOF

from scrapy import Spider, Item, Field

class Post(Item):

title = Field()

class BlogSpider(Spider):

name, start_urls = ‘blogspider‘, [‘http://www.cnblogs.com/rwxwsblog/‘]

def parse(self, response):

return [Post(title=e.extract()) for e in response.css("h2 a::text")]

EOF

27  scrapy runspider myspider.py

scrapy startproject gl