python採集百度搜索結果帶有特定URL的連結程式碼例項
阿新 • • 發佈:2020-01-09
這篇文章主要介紹了python採集百度搜索結果帶有特定URL的連結程式碼例項,文中通過示例程式碼介紹的非常詳細,對大家的學習或者工作具有一定的參考學習價值,需要的朋友可以參考下
#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',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})#獲得從百度搜索出來的a標籤的連結 for bq in bqs: r = requests.get(bq['href'],timeout=3)#獲取真實連結 if r.status_code == 200:#如果狀態碼為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() #執行格式 python aaaaa.py "inurl:asp?id=" -p 30 -t 30
以上就是本文的全部內容,希望對大家的學習有所幫助,也希望大家多多支援我們。