爬虫-requests

本人之前的requests文章

实例:(使用IP代理池,去分页下载爱思官网的铃声)

#ulits.py工具模块中
	

import re
import random

RE_MP3_STEMPLE = re.compile(r'height="28"  alt="(.*?)" title')
RE_MP3_URL = re.compile(r'data-mp3="(.*?).mp3"')

HEADER = {
    "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.79 Safari/537.36"
}
Request_is_ok = ' 请求成功...'
Response_is_ok = '响应成功...'
WORK = ' 解析完毕,现在开始下载歌曲...'
NUMBERS = 1

def IP_list():
    IP = [
        {'https://':'112.14.47.6:52024'},
        {'https://''171.35.175.112:9999'},
        {'https://':'113.195.157.253'},
        {'https://':'123.55.98.129:9999'},
        {'https://':'123.55.98.129:8080'}
    ]
    IP_index =  random.randint(0,4)
    return IP[IP_index]




#urlib3.py主项目中
	
import re
from random import randint
from time import sleep
import requests
from pachong.utils import RE_MP3_STEMPLE,HEADER,Request_is_ok,RE_MP3_URL,WORK

IP = [
    {'https://': '112.14.47.6:52024'},
    {'https://':'171.35.175.112:9999'},
    {'https://': '113.195.157.253'},
    {'https://': '123.55.98.129:9999'},
    {'https://': '123.55.98.129:8080'}
]

def MP3_NAME_URL()              ->list:
    NUMBERS = 1
    for v in range(1,501):
        PROJECT_URL = f'https://www.i4.cn/ring_4_5_{v}.html'
        response = requests.get(url=PROJECT_URL,headers=HEADER)
        if response.status_code == 200:
            response = response.text
            print(f' 第{v}页{Request_is_ok}请稍后...')
            sleep(3)
            MP3_name = re.findall(RE_MP3_STEMPLE,response)
            MP3_URL = re.findall(RE_MP3_URL,response)
            print(f' 第{v}页{WORK}请稍后...')
            sleep(3)
            for i in range(len(MP3_URL)):
                IPNOW = IP[randint(0,4)]
                print(f" 使用{IPNOW.get('https://')}来下载!")
                url = MP3_URL[i]
                print(f" URL:{url}",'\n' + f' NAME:{MP3_name[i]}' + '\n' + '-'* 130)
                resalt = requests.get(url=url,headers=HEADER,proxies=IPNOW).content
                try:
                    with open(f'./ll/{MP3_name[i]}.mp3','wb') as f:
                        f.write(resalt)
                        sleep(0.2)
                        NUMBERS += 1
                        print(f' 开始下载第{NUMBERS}首...')
                except FileNotFoundError:
                    File_error = True
                    print( '找不到根路径ll文件夹,即将终止下载...')
                    break
        else:
            print('请求失败,请尝试稍后在操作...')


if __name__ == '__main__':
    MP3_NAME_URL()