python实现的一只从百度开始不断搜索的小爬虫

程序员文章站 2022-03-18 19:42:29

文中用到了beautifulsoup这个库，目的是处理html文档分析的，因为我只是提取了title的关键字，所以可以用正则表达式代替，还有一个库是jieba，这个...

文中用到了beautifulsoup这个库，目的是处理html文档分析的，因为我只是提取了title的关键字，所以可以用正则表达式代替，还有一个库是jieba，这个库是中文分词的作用，再有一个库是 chardet，用来判断字符的编码，本想多线程的，但是自认为被搞糊涂了，就放弃了

复制代码代码如下:

#coding:utf-8
import re
import urllib
import urllib2
import sys
import time
import queue
import thread
import threading
import jieba
import chardet
from beautifulsoup import beautifulsoup as bs

deep = 1000
lock = threading.lock()
path = "c:\\test\\"
urlqueue = queue.queue()
def pachong():
url = 'http://www.baidu.com'
return url

def getpageurl(html):
reurl = re.compile(r'<\s*[aa]{1}\s+[^>]*?[hh][rr][ee][ff]\s*=\s*[\"\']?([^>\"\']+)[\"\']?.*?>')
urls = reurl.findall(html)
for url in urls:
  if len(url) > 10:
   if url.find('javascript') == -1:
    urlqueue.put(url)

def getcontents(url):
try:
  url = urllib2.quote(url.split('#')[0].encode('utf-8'), safe = "%/:=&?~#+!$,;'@()*[]")
  req = urllib2.urlopen(url)
  res = req.read()
  code = chardet.detect(res)['encoding']
  #print
  #print code
  res = res.decode(str(code), 'ignore')
  res = res.encode('gb2312', 'ignore')
  code = chardet.detect(res)['encoding']
  #print code
  #print res
  return res
except urllib2.httperror, e:
  print e.code
  return none
except urllib2.urlerror, e:
  print str(e)
  return none

def writetofile(html, url):
fp = file(path + str(time.time()) + '.html', 'w')
fp.write(html)
fp.close()

def getkeywords(html):
code = chardet.detect(html)['encoding']
if code == 'iso-8859-2':
  html.decode('gbk', 'ignore').encode('gb2312', 'ignore')
code = chardet.detect(html)['encoding']
soup = bs(html, fromencoding="gb2312")
titletag = soup.title
titlekeywords = titletag.contents[0]
cutwords(titlekeywords)

def cutwords(contents):
print contents
res = jieba.cut_for_search(contents)
res = '\n'.join(res)
print res
res = res.encode('gb2312')
keywords = file(path + 'cutkeywors.txt', 'a')
keywords.write(res)
keywords.close()

def start():

while urlqueue.empty() == false:
  url = urlqueue.get()
  html = getcontents(url)
  getpageurl(html)
  getkeywords(html)
  #writetofile(html, url)

if __name__ == '__main__':
starturl = pachong()
urlqueue.put(starturl)
start()

上一篇： How to solve "Error: Cannot find module '../lib/cli'" when create a new project by webstorm.

下一篇：详解C++构造函数

python实现的一只从百度开始不断搜索的小爬虫