Python爬虫实现爬取下载网站数据的几种方法示例

import requests
url = 'xxxxxxxx'  # 目标下载链接
r = requests.get(url)  # 发送请求
# 保存
with open ('r.txt', 'rb') as f:
    f.write(r.content)
    f.close

安装 wget 库

pip install wget

import wget
url = 'https://pic.cnblogs.com/avatar/1197773/20170712160655.png'  # 目标路由，下载的资源是图片
path = 'D:/x.png'  # 保存的路径
wget.download(url, path)  # 下载

import requests
url = 'https://readthedocs.org/projects/python-guide/downloads/pdf/latest'
# allow_redirect参数True表示允许重定向
r = requests.get(url, allow_redirect=True)
with open('r.txt', 'wb') as f:
    f.write(r)
    f.close()

import requests
url = 'https://readthedocs.org/projects/python-guide/downloads/pdf/latest'
# stream参数True表示分块下载
r = requests.get(url, stream=True)
with open('r.txt', 'wb') as f:
    for ch in r:
        f.write(r)
    f.close()

import requests
from multiprocessing.poll import Pool
# 定义下载函数
def url_response(url):
    path, url = url
    r = requests.get(url, stream=True)
    with open(path, 'wb') as f:
        for ch in r:
            f.write(ch)
        f.close()
urls = ['aaa', 'bbb', 'ccc']  # 假设有好多个下载链接
# 排队下载的方式
for x in urls:
    url_response(x)
# 并行下载的方式
ThreadPool(3).imap_unordered(url_response, urls)

pip install clint

import requests
from clint.textui import progess
url = 'xxxxxxxxxxx'
r = requests.get(url, stream=True)
with open('x.txt', 'wb') as f
    total_length = int(r.headers.get('content-length'))
    for ch in progress.bar(r.iter_content(chunk_size=2391975, expected)size=(total_length/1024)+1)):
        if ch:
            f.write(ch)
    f.close()

urllib.request.urlretrieve(URL, PATH)

import requests
# 定义代理，假设本机上有个梯子的服务，代理端口是2258
proxy = {'http': 'http://127.0.0.1:2258'} 
url = 'xxxxxx'
r = requests.get(url, proxies=proxy )
.......

import urllib.request
#Python小白学习交流群：153708845
url = 'xxxxxxxxxx'
proxy = urllib.request.ProxyHandler({'http': '127.0.0.1'})
open_proxy = urllib.request.build_opener(proxy )  # 打开代理
urllib.request.urlretrieve(url)

pip install urllib3