python采集百度搜索结果带有特定URL的链接代码实例

Ella ·

更新时间:2024-09-21

· 588 次阅读

这篇文章主要介绍了python采集百度搜索结果带有特定URL的链接代码实例,文中通过示例代码介绍的非常详细，对大家的学习或者工作具有一定的参考学习价值,需要的朋友可以参考下


#coding utf-8
import requests
from bs4 import BeautifulSoup as bs
import re
from Queue import Queue
import threading
from argparse import ArgumentParser
arg = ArgumentParser(description='baidu_url_collet py-script by xiaoye')
arg.add_argument('keyword',help='keyword like inurl:?id=for searching sqli site')
arg.add_argument('-p','--page',help='page count',dest='pagecount',type=int)
arg.add_argument('-t','--thread',help='the thread_count',dest='thread_count',type=int,default=10)
arg.add_argument('-o','--outfile',help='the file save result',dest='oufile',type=int,default='result.txt')
result = arg.parse_args()
headers = {'User-Agent':'Mozilla/5.0(windows NT 10.0 WX64;rv:50.0) Gecko/20100101 Firefox/50.0'}
class Bg_url(threading.Thread):
  def __init__(self,que):
    threading.Thread.__init__(self)
    self._que = que
  def run(self):
    while not self._que.empty():
      URL = self._que.get()
      try:
        self.bd_url_collet(URL)
      except Exception,e:
        print(e)
        pass
  def bd_url_collect(self, url):
    r = requests.get(url, headers=headers, timeout=3)
    soup = bs(r.content, 'lxml', from_encoding='utf-8')
    bqs = soup.find_all(name='a', attrs={‘data-click‘:re.compile(r'.'), 'class':None})#获得从百度搜索出来的a标签的链接
    for bq in bqs:
      r = requests.get(bq['href'], headers=headers, timeout=3)#获取真实链接
      if r.status_code == 200:#如果状态码为200
        print r.url
        with open(result.outfile, 'a') as f:
          f.write(r.url + '\n')
def main():
  thread = []
  thread_count = result.thread_count
  que = Queue()
  for i in range(0,(result.pagecount-1)*10,10):
  que.put('https://www.baidu.com/s?wd=' + result.keyword + '&pn=' + str(i))
  or i in range(thread_count):
  thread.append(Bd_url(que))
  for i in thread:
    i.start()
  for i in thread:
    i.join()    
if __name__ == '__main__':
  main()  
#执行格式
python aaaaa.py "inurl:asp?id=" -p 30 -t 30

您可能感兴趣的文章:python采集百度百科的方法Python爬虫:url中带字典列表参数的编码转换方法解决安装python3.7.4报错Can''''t connect to HTTPS URL because the SSL module is not availablePython3模拟curl发送post请求操作示例python re正则匹配网页中图片url地址的方法Python2和Python3中urllib库中urlencode的使用注意事项python爬虫之urllib3的使用示例python 重定向获取真实url的方法

百度搜索 Python url

1024 个赞