python利用百度做url采集

pip install tableprintparamiko==2.0.8语法：python url_collection.py -h输出帮助信息python url_collection.py 要采集的信息 -p 页数 -t 进程数 -o 保存的文件名以及格式新建文件touch url_collection.py写入代码正式部分

#coding: utf-8

import requestsfrom bs4 import BeautifulSoup as bsimport refrom Queue import Queueimport threadingfrom argparse import ArgumentParserlogo="""u u l | ccccc ooooo l l eeeeee cccccc tttttttu u r rr l | c o o l l e c tu u r r r l | c o o l l eeeeee c tu u r l | c o o l l e c tu u u r l | c o o l l e c tuuuuuuuu u r lllll | ccccc ooooo llllll lllll eeeeee cccccc tBy : Snow wolf"""print(logo)arg = ArgumentParser(description='baidu_url_collect py-script by snowwolf')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='outfile', default='result.txt')result = arg.parse_args()headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:50.0) Gecko/20100101 Firefox/50.0'}

class Bd_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_collect(URL)        except Exception,e:            print e            passdef 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})        for bq in bqs:            r = requests.get(bq['href'], headers=headers, timeout=3)            if r.status_code == 200:                print r.url                with open(result.outfile, 'a') as f:                    f.write(r.url + '\n')

def main():

thread = []thread_count = result.thread_countque = Queue()for i in range(0,(result.pagecount-1)*10,10):que.put('=' + result.keyword + '&pn=' + str(i))

for 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()

代码结束