有人知道我可以使用基于Python的优秀网络爬虫吗？

Question

我很想写自己的，但我现在没有足够的时间。我已经看过open source crawlers的维基百科列表，但我更喜欢用Python编写的东西。我意识到我可能只是使用维基百科页面上的一个工具并将其包装在Python中。我可能最终会这样做 - 如果有人对这些工具有任何建议，我愿意听到他们的意见。我通过它的网络界面使用了Heritrix，我发现它非常麻烦。我绝对不会在即将推出的项目中使用浏览器API。

提前致谢。另外，这是我的第一个问题！

Answer 1

• Mechanize是我最喜欢的;卓越的高级浏览功能（超简单的表单填写和提交）。
• Twill是一种构建于Mechanize
之上的简单脚本语言
• BeautifulSoup + urllib2也很有效。
• Scrapy看起来像是一个非常有前途的项目;这是新的。

Answer 2

使用Scrapy。

这是一个基于扭曲的网络爬虫框架。仍处于重大发展阶段，但已经有效。有很多好东西：

• 内置支持解析HTML，XML，CSV和Javascript
• 用于使用图像（或任何其他媒体）抓取项目并下载图像文件的媒体管道
• 支持通过使用中间件，扩展和管道插入您自己的功能来扩展Scrapy
• 广泛的内置中间件和扩展，用于处理压缩，缓存，Cookie，身份验证，用户代理欺骗，robots.txt处理，统计信息，抓取深度限制等
• 交互式抓取shell控制台，对开发和调试非常有用
• 用于监控和控制机器人的Web管理控制台
• 用于低级访问Scrapy流程的Telnet控制台

通过在返回的HTML上使用XPath选择器提取有关今天在mininova torrent网站中添加的所有torrent文件的信息的示例代码：

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]

Answer 3

检查HarvestMan，一个用Python编写的多线程Web爬虫，还可以查看spider.py模块。

here您可以找到代码示例来构建一个简单的网络抓取工具。

Answer 4

我使用Ruya并发现它非常好。

Answer 5

我攻击了上面的脚本以包含一个登录页面，因为我需要它来访问一个drupal站点。不漂亮，但可以帮助那里的人。

#!/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\n' % 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\n' % 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 "\nLogging in", url_login_link
  x = mySpider.loginSite( url_login_link )

  while link != '':

    print "\nChecking 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 "\ndone\n"

if __name__ == "__main__":
  main()

Answer 6

相信我没有什么比卷曲更好......以下代码可以在Amazon EC2

上在不到300秒的时间内并行抓取10,000个URL

注意： 不要以如此高的速度点击同一个域..

#! /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()

Answer 7

另一个simple spider 使用BeautifulSoup和urllib2。没有什么太复杂，只是读取所有href的构建列表并继续它。

Answer 8

pyspider.py