技術標籤：python

@[TOC]新手的一個小漫畫爬蟲

一、爬蟲小程式碼

爬取的是http://www.js518.net/的漫畫，只能一話一話的下載，記錄一下程式碼的成長

#coding: UTF-8

from bs4 import BeautifulSoup
from selenium import webdriver
import urllib.request
import os
import time

def Requ(url):#定義一個可以獲取圖片的位元組碼的方法
    headers = {"User-agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 11_1_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.22 Safari/537.36"
 
}
    requ =urllib.request.Request(url,headers = headers)
    html = urllib.request.urlopen(requ).read()
    return html

def PicUrl(url,bq,id):
    driver = webdriver.Chrome()
    openurl = driver.get(url)
    html = driver.page_source
    driver.quit()
    soup = BeautifulSoup(html,'html.parser')
    return
 
 soup.find(bq,id=id)

if __name__ == '__main__':
    print("漫畫網址：******,搜素你要看的漫畫後，將網址輸入：")
    url = input()
    a = PicUrl(url,'span','k_total').next_element
    for i in range(1,int(a)+1):
        rullurl = url+r'?p='+str(i)
        picurl = PicUrl(rullurl,'img','qTcms_pic').get('src')
        with
 
 open(os.getcwd()+'\\2\\'+'%d.jpg'%i,'wb')as f:#寫入檔案，應加入檔名和檔案位置
            f.write(Requ(picurl))
            time.sleep(1)
            print("save %d pic"%i)
    print('save end!')

`