python 實現爬取網站下全部URL

 

 

python3 實現爬取網站下全部URL

• 獲取首頁元素信息：
• 首頁的URL連接獲取：
• 遍歷第一次返回的結果：
• 遞歸循環遍歷：
• 所有代碼以下：
• 小結：

 

• python3.6
• requests && bs4
• 採用遞歸方法，最終爬取網站全部連接

獲取首頁元素信息：

目標 test_URL：http://www.xxx.com.cn/
首先檢查元素，a 標籤下是咱們須要爬取得連接，經過獲取連接路徑，定位出咱們須要的信息

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

首頁的URL連接獲取：

完成首頁的URL連接獲取，具體代碼以下：

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)

遍歷第一次返回的結果：

從第二步獲取URL的基礎上，遍歷請求每一個頁面，獲取頁面中的URL連接，過濾掉不須要的信息
具體代碼以下：

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))

遞歸循環遍歷：

遞歸實現爬取全部url，在get_next_url()函數中調用自身，代碼以下：

get_next_url(url_list2)

所有代碼以下：

#!/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)

小結：

剛開始學習寫python腳本，有不足之處，多多指導，有一個小bug,後期會進一步完善。