渗透利器-kali工具 (第四章-6) 爬虫编写

本文内容:

  • 从官方文档学习模块
  • 实战爬取数据
  • 脚本实现爬取url

1,从官方文档学习模块:

  调用help函数,可以看到一个函数或者方法的字符串文档

  help(name)       很详细的模块文档

  help(range)       很详细的类的文档

  help(time.localtime())     很详细的函数文档

  举例:

    print(time.__doc__)  较详细的模块文档

    print(time.localtime().__doc__)  较详细的函数文档

    print(range.__doc__)  较详细的类的文档

  使用dir可以查看模块或对象都有哪些方法:

    dir(requests)           将requests模块的方法显示出来

    print(dri(time))         简略的模块函数显示

    print(dir(time.localtime()))  简略的函数参数显示

    print(dir(range))       简略的类构造函数参数显示

  使用ipython+?查看:

    requests.get?

  Python中官方文档:https://docs.python.org/zh-cn/3

  Pytcharm中查看快速帮助和Python官方帮助文档:

    把光标放在要查询的对象上,打开视图菜单,quick definition查看对象的定义

    quick documentation 快速文档,这个是jet brains自己对Python的解释文档

    第三个external documentation 外部文档,这个是Python的官方帮助文档,跳转到网页帮助文档中。

2,实战爬取数据:

  1.爬取图片:

    1.思路:

      根据我们输入的关键字在百度进行抓取图片并下载,最后给我们推荐:

      所需模块:

        import re    筛选所要的内容

        import requests  网路请求模块[获取网页信息]

        from urllib import error  异常模块

        from bs4 import BeautifulSoup  解析网页内容

        import os        文件操作模块

    2.代码实现:

import re
import requests
from urllib import error
from bs4 import BeautifulSoup
import os

num = 0
numPicture = 0
file = ' '
List = []

def Find(url):
    global List
    print('正在检测图片总数量,稍等...')
    t = 0
    i = 1
    s = 0
    while t < 1000:
        Url = url +str(t)
        try:
            Result = requests.get(Url,timeout = 7)
        except BaseException:
            t = t + 60
            continue
        else:
            result = Result.text
            pic_url = re.findall('"objURL":"(.*?)",',result,re.S)
            s += len(pic_url)
            if len(pic_url) == 0:
                break
            else:
                List.append(pic_url)
                t = t + 60
    return s

def recommend(url):
    Re = []
    try:
        html = requests.get(url)
    except error.HTTPError as e:
        return
    else:
        html.encoding = 'utf-8'
        bsobj = BeautifulSoup(html.text,'html.parser')
        div = bsobj.find('div',id='topRS')
        if div is not None:
            listA = div.findAll('a')
            for i in listA:
                if i is not None:
                    Re.append(i.get_text())
        return Re

def dowmloadPicture(html,keyword):
    global num
    pic_url = re.findall('"objURL":"(.*?)",',html,re.S)
    print('找到关键词:' + keyword + '的图片,即将开始下载...')
    for each in pic_url:
        print('正在下载第' + str(num + 1) + '张图,图片地址:' + str(each))
        try:
            if each is not None:
                pic = requests.get(each,timeout=7)
            else:
                continue
        except BaseException:
            print('错了,当前图片不能下载')
            continue
        else:
            string = file + r'\' +keyword + '_' +str(num) +'.jpg'
            fp = open(string,'wb')
            fp.write(pic.content)
            fp.close()
            num += 1
        if num >= numPicture:
            return



if __name__ == '__main__':
    word = input("请输入搜索关键词(可以是人名,地名等):")
    url='http://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word='+word+'&pn='
    tot=Find(url)
    Recommend=recommend(url)# 记录相关推荐
    print('经过检测%s类图片共有%d张'%(word,tot))
    numPicture=int(input('请输入想要下载的图片数量'))
    file=input('请建立一个存储图片的文件夹,输入文件夹名称即可')
    y=os.path.exists(file)
    if y == 1:
        print('该文件已存在,请重新输入')
        file=input('请建立一个存储图片的文件夹,输入文件夹名称即可')
    else:
        os.mkdir(file)
    # while True:
    #     file = input('请建立一个存储图片的文件夹,输入文件夹名称即可')
    #     if os.path.exists(file):
    #         continue
    #     else:
    #         break
    # file = 'D:/pythonlianxi/web_png'
    t=0
    tmp=url
    while t< numPicture:
        try:
            url=tmp + str(t)
            result=requests.get(url,timeout=10)
            print(url)
        except error.HTTPError as e:
            print('网络错误,请调整网络后重试')
            t = t+60
        else:
            dowmloadPicture(result.text,word)
            t = t + 60
    print('你还想看')
    for re in Recommend:
        print(re,end=" ")

   2.爬取URL:

    1.代码实现:

      使用命令: web_pc.py -p 页数 -t 线程 -o 文件名 关键词

      解释: 

        web_pc.py:文件名称

        关键字:可是使用Google Hacking语法

import requests,re,threading,time
from bs4 import BeautifulSoup as bs
from queue import Queue
from argparse import ArgumentParser

arg = ArgumentParser(description='baidu_url_collection')
arg.add_argument('keyword',help='inurl:.asp?id=1')
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/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)'}

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 as e:
                print ('Exception: ',e)
                pass

    def bd_url_collect(self, url):

            r = requests.get(url, headers=headers, timeout=5)

            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=5)
                if r.status_code == 200:
                    print(r.url)

                    with open(result.outfile, 'a+') as f:
                        f.write(r.url + '
')
                    # result.outfile.close()

def main():
    thread = []
    thread_count = result.thread_count
    que = Queue()
    for i in range(0,(result.pagecount)):
        que.put('https://www.baidu.com/s?wd=' + 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__':

    start = time.perf_counter()
    main()
    end = time.perf_counter()
原文地址:https://www.cnblogs.com/xz25/p/12908483.html