python 实现爬取网站下所有URL

  • python3.6
  • requests && bs4
  • 采用递归方法,最终爬取网站所有链接

获取首页元素信息:

目标 test_URL:http://www.xxx.com.cn/
首先检查元素,a 标签下是我们需要爬取得链接,通过获取链接路径,定位出我们需要的信息

soup = Bs4(reaponse.text, "lxml")
urls_li = soup.select("#mainmenu_top > div > div > ul > li")

首页的URL链接获取:

完成首页的URL链接获取,具体代码如下:

def get_first_url():
    list_href = []
    reaponse = requests.get("http://www.xxx.com.cn", headers=headers)
    soup = Bs4(reaponse.text, "lxml")
    urls_li = soup.select("#mainmenu_top > div > div > ul > li")
    for url_li in urls_li:
        urls = url_li.select("a")
        for url in urls:
            url_href = url.get("href")
            list_href.append(head_url+url_href)
            out_url = list(set(list_href))
    for reg in out_url:
        print(reg)

遍历第一次返回的结果:

从第二步获取URL的基础上,遍历请求每个页面,获取页面中的URL链接,过滤掉不需要的信息
具体代码如下:

def get_next_url(urllist):
    url_list = []
    for url in urllist:
        response = requests.get(url,headers=headers)
        soup = Bs4(response.text,"lxml")
        urls = soup.find_all("a")
        if urls:
            for url2 in urls:
                url2_1 = url2.get("href")
                if url2_1:
                    if url2_1[0] == "/":
                        url2_1 = head_url + url2_1
                        url_list.append(url2_1)
                        if url2_1[0:24] == "http://www.xxx.com.cn":
                            url2_1 = url2_1
                            url_list.append(url2_1)
                        else:
                            pass
                    else:
                        pass
                else:
                    pass
        else:
            pass
    url_list2 = set(url_list)
    for url_ in url_list2:
        res = requests.get(url_)
        if res.status_code ==200:
            print(url_)
    print(len(url_list2))

递归循环遍历:

递归实现爬取所有url,在get_next_url()函数中调用自身,代码如下:

get_next_url(url_list2)

全部代码如下:

#!/usr/bin/env python 
# -*- coding:utf-8 -*-

import requests
from bs4 import BeautifulSoup as Bs4

head_url = "http://www.xxx.com.cn"
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36"
}
def get_first_url():
    list_href = []
    reaponse = requests.get(head_url, headers=headers)
    soup = Bs4(reaponse.text, "lxml")
    urls_li = soup.select("#mainmenu_top > div > div > ul > li")
    for url_li in urls_li:
        urls = url_li.select("a")
        for url in urls:
            url_href = url.get("href")
            list_href.append(head_url+url_href)
            out_url = list(set(list_href))
    return out_url


def get_next_url(urllist):
    url_list = []
    for url in urllist:
        response = requests.get(url,headers=headers)
        soup = Bs4(response.text,"lxml")
        urls = soup.find_all("a")
        if urls:
            for url2 in urls:
                url2_1 = url2.get("href")
                if url2_1:
                    if url2_1[0] == "/":
                        url2_1 = head_url + url2_1
                        url_list.append(url2_1)
                        if url2_1[0:24] == "http://www.xxx.com.cn":
                            url2_1 = url2_1
                            url_list.append(url2_1)
                        else:
                            pass
                    else:
                        pass
                else:
                    pass
        else:
            pass
    url_list2 = set(url_list)
    for url_ in url_list2:
        res = requests.get(url_)
        if res.status_code ==200:
            print(url_)
    print(len(url_list2))
    get_next_url(url_list2)


if __name__ == "__main__":
    urllist = get_first_url()
    get_next_url(urllist)

小结:

刚开始学习写python脚本,有不足之处,多多指导,有一个小bug,后期会进一步完善。

原文地址:https://www.cnblogs.com/dddjh/p/10753588.html