scrapy递归下载网站
?# encoding: utf-8
import os
import re
import subprocess
import sys
import chardet
import scrapy
from scrapy.http import Request
from scrapy.selector import HtmlXPathSelector
from scrapy.spider import BaseSpider
from scrapy.utils.url import urljoin_rfc
from mychardet import *
# print sys.getdefaultencoding()
# print sys.path
def get_default_to_codec():
return mytogb18030
def getfirst(a):
# print ‘enter getfirst‘, repr(a)
if a == None:
return u‘‘
elif len(a) == 0:
return u‘‘
b = a[0]
# print repr(b)#, chardet.detect(b)
return b
class Greasemonkey1Spider(scrapy.Spider):
name = "test"
allowed_domains = ["localhost"]
start_urls = (
‘http://localhost/test‘,
)
def parseContext(self, response):
# print "Enter parseContext: ", response.url
hxs = response
sel = hxs.xpath(‘//title/text()‘)
if sel != None:
titles = sel.extract()
if len(titles) > 0: title = titles[0]
else: title = ‘‘
sel = hxs.xpath(‘/html/body‘)
if sel != None:
bodys = sel.extract()
if len(bodys) > 0: body = bodys[0]
else: body = ‘‘
# print title, repr(body)
def parse(self, response):
baseurl = response.url
print ‘baseurl = ‘, baseurl
self.parseContext(response)
hxs = response.xpath(r‘//a‘)
for path in hxs:
titles = getfirst(path.xpath(r‘text()‘).extract())
urls = getfirst(path.xpath(r‘@href‘).extract())
# print titles, urls
item_url = urljoin_rfc(baseurl, urls)
yield Request(item_url,callback=self.parse)
if __name__ == ‘__main__‘:
cmd = ‘‘‘E:\Python27\Scripts\scrapy.exe crawl --nolog test‘‘‘
cwd = os.path.split(__file__)[0]
p = subprocess.Popen(cmd.split(), stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=False, cwd=cwd)
while None == p.poll():
out, err = p.communicate()
# print ‘out, err‘, out, err, repr(out), repr(err)
if err:
print err
elif out:
print out
print p.returncode
# while not p.poll():
# print p.stdout.read()
# print p.stderr.read()
郑重声明:本站内容如果来自互联网及其他传播媒体,其版权均属原媒体及文章作者所有。转载目的在于传递更多信息及用于网络分享,并不代表本站赞同其观点和对其真实性负责,也不构成任何其他建议。