我对自己写一个爬虫感到半信半疑，但我现在时间不够。我看过维基百科上的开源爬虫列表，但我更喜欢使用Python编写。我意识到我可以直接使用维基页上的工具，并在Python中进行包装。如果有人对这些工具有任何建议，我很愿意听取。我已经通过其Web接口使用过Heritrix，但我发现它非常繁琐。我肯定不会在我的即将到来的项目中使用浏览器API。
提前感谢。此外，这是我第一个 Stack Overflow 的问题！
使用Scrapy。
这是一个基于Twisted的网络爬虫框架，仍在积极开发中，但已经可以使用。具有许多好处：
通过在返回的HTML上使用XPath选择器，提取所有今天添加到mininova种子站的种子文件信息的示例代码：
class Torrent(ScrapedItem):
pass
class MininovaSpider(CrawlSpider):
domain_name = mininova.org
start_urls = [ http://www.mininova.org/today ]
rules = [Rule(RegexLinkExtractor(allow=[ /tor/d+ ]), parse_torrent )]
def parse_torrent(self, response):
x = HtmlXPathSelector(response)
torrent = Torrent()
torrent.url = response.url
torrent.name = x.x("//h1/text()").extract()
torrent.description = x.x("//div[@id= description ]").extract()
torrent.size = x.x("//div[@id= info-left ]/p[2]/text()[2]").extract()
return [torrent]
请查看用Python编写的多线程网络爬虫HarvestMan，还要看一下spider.py模块。 HarvestMan spider.py
这里有代码示例，可以构建一个简单的网络爬虫。
我使用过Ruya，觉得它相当不错。
我黑客攻击了上述脚本，加入了一个登录页面，因为我需要它来访问一个Drupal网站。 不太美观，但可能会帮助那里的某个人。
#!/usr/bin/python
import httplib2
import urllib
import urllib2
from cookielib import CookieJar
import sys
import re
from HTMLParser import HTMLParser
class miniHTMLParser( HTMLParser ):
viewedQueue = []
instQueue = []
headers = {}
opener = ""
def get_next_link( self ):
if self.instQueue == []:
return
else:
return self.instQueue.pop(0)
def gethtmlfile( self, site, page ):
try:
url = http:// +site+ +page
response = self.opener.open(url)
return response.read()
except Exception, err:
print " Error retrieving: "+page
sys.stderr.write( ERROR: %s
% str(err))
return ""
return resppage
def loginSite( self, site_url ):
try:
cj = CookieJar()
self.opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
url = http:// +site_url
params = { name : customer_admin , pass : customer_admin123 , opt : Log in , form_build_id : form-3560fb42948a06b01d063de48aa216ab , form_id : user_login_block }
user_agent = Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)
self.headers = { User-Agent : user_agent }
data = urllib.urlencode(params)
response = self.opener.open(url, data)
print "Logged in"
return response.read()
except Exception, err:
print " Error logging in"
sys.stderr.write( ERROR: %s
% str(err))
return 1
def handle_starttag( self, tag, attrs ):
if tag == a :
newstr = str(attrs[0][1])
print newstr
if re.search( http , newstr) == None:
if re.search( mailto , newstr) == None:
if re.search( # , newstr) == None:
if (newstr in self.viewedQueue) == False:
print " adding", newstr
self.instQueue.append( newstr )
self.viewedQueue.append( newstr )
else:
print " ignoring", newstr
else:
print " ignoring", newstr
else:
print " ignoring", newstr
def main():
if len(sys.argv)!=3:
print "usage is ./minispider.py site link"
sys.exit(2)
mySpider = miniHTMLParser()
site = sys.argv[1]
link = sys.argv[2]
url_login_link = site+"/node?destination=node"
print "
Logging in", url_login_link
x = mySpider.loginSite( url_login_link )
while link != :
print "
Checking link ", link
# Get the file from the site and link
retfile = mySpider.gethtmlfile( site, link )
# Feed the file into the HTML parser
mySpider.feed(retfile)
# Search the retfile here
# Get the next link in level traversal order
link = mySpider.get_next_link()
mySpider.close()
print "
done
"
if __name__ == "__main__":
main()
相信我，没有什么比卷曲更好了。以下代码可以在Amazon EC2上以不到300秒的时间并行爬取10,000个网址。
注意：不要以如此高速攻击同一个域名。
#! /usr/bin/env python
# -*- coding: iso-8859-1 -*-
# vi:ts=4:et
# $Id: retriever-multi.py,v 1.29 2005/07/28 11:04:13 mfx Exp $
#
# Usage: python retriever-multi.py <file with URLs to fetch> [<# of
# concurrent connections>]
#
import sys
import pycurl
# We should ignore SIGPIPE when using pycurl.NOSIGNAL - see
# the libcurl tutorial for more info.
try:
import signal
from signal import SIGPIPE, SIG_IGN
signal.signal(signal.SIGPIPE, signal.SIG_IGN)
except ImportError:
pass
# Get args
num_conn = 10
try:
if sys.argv[1] == "-":
urls = sys.stdin.readlines()
else:
urls = open(sys.argv[1]).readlines()
if len(sys.argv) >= 3:
num_conn = int(sys.argv[2])
except:
print "Usage: %s <file with URLs to fetch> [<# of concurrent connections>]" % sys.argv[0]
raise SystemExit
# Make a queue with (url, filename) tuples
queue = []
for url in urls:
url = url.strip()
if not url or url[0] == "#":
continue
filename = "doc_%03d.dat" % (len(queue) + 1)
queue.append((url, filename))
# Check args
assert queue, "no URLs given"
num_urls = len(queue)
num_conn = min(num_conn, num_urls)
assert 1 <= num_conn <= 10000, "invalid number of concurrent connections"
print "PycURL %s (compiled against 0x%x)" % (pycurl.version, pycurl.COMPILE_LIBCURL_VERSION_NUM)
print "----- Getting", num_urls, "URLs using", num_conn, "connections -----"
# Pre-allocate a list of curl objects
m = pycurl.CurlMulti()
m.handles = []
for i in range(num_conn):
c = pycurl.Curl()
c.fp = None
c.setopt(pycurl.FOLLOWLOCATION, 1)
c.setopt(pycurl.MAXREDIRS, 5)
c.setopt(pycurl.CONNECTTIMEOUT, 30)
c.setopt(pycurl.TIMEOUT, 300)
c.setopt(pycurl.NOSIGNAL, 1)
m.handles.append(c)
# Main loop
freelist = m.handles[:]
num_processed = 0
while num_processed < num_urls:
# If there is an url to process and a free curl object, add to multi stack
while queue and freelist:
url, filename = queue.pop(0)
c = freelist.pop()
c.fp = open(filename, "wb")
c.setopt(pycurl.URL, url)
c.setopt(pycurl.WRITEDATA, c.fp)
m.add_handle(c)
# store some info
c.filename = filename
c.url = url
# Run the internal curl state machine for the multi stack
while 1:
ret, num_handles = m.perform()
if ret != pycurl.E_CALL_MULTI_PERFORM:
break
# Check for curl objects which have terminated, and add them to the freelist
while 1:
num_q, ok_list, err_list = m.info_read()
for c in ok_list:
c.fp.close()
c.fp = None
m.remove_handle(c)
print "Success:", c.filename, c.url, c.getinfo(pycurl.EFFECTIVE_URL)
freelist.append(c)
for c, errno, errmsg in err_list:
c.fp.close()
c.fp = None
m.remove_handle(c)
print "Failed: ", c.filename, c.url, errno, errmsg
freelist.append(c)
num_processed = num_processed + len(ok_list) + len(err_list)
if num_q == 0:
break
# Currently no more I/O is pending, could do something in the meantime
# (display a progress bar, etc.).
# We just call select() to sleep until some more data is available.
m.select(1.0)
# Cleanup
for c in m.handles:
if c.fp is not None:
c.fp.close()
c.fp = None
c.close()
m.close()
Another simple spider Uses BeautifulSoup and urllib2. Nothing too sophisticated, just reads all a href s builds a list and goes though it.