Python requests+BeautifulSoup爬虫（下载图片）

1、导入库

import requests
from bs4 import BeautifulSoup

2、下载图片流程 

【网址https://wall.alphacoders.com/】【若有侵权，请联系1150646501@qq.com，立马删除】

正常手动下载图片流程

1）访问https://wall.alphacoders.com/

2）点击图片进入新的链接

3）保存图片

python代码下载流程

1）获取https://wall.alphacoders.com/网页源代码

2）找到图片点击后对应链接（假设为xxx）

3）获取xxx网页源代码(假设为yyy)

4）找到yyy中图片链接（假设为zzz.jpg）

5)下载图片

【代码如下】

1）获取https://wall.alphacoders.com/网页源代码



# -*- encoding=utf-8 -*-

import requests
from bs4 import BeautifulSoup


# 获取网页源代码
def get_html(url='https://wall.alphacoders.com/'):
    ret = requests.get(url)
    # 获取返回的状态 200表示请求成功
    print ret.status_code
    html = ret.text
    # 网页源代码
    # print html
    return html


if __name__ == '__main__':
    pass




2）找到图片点击后对应链接（假设为xxx）


通过查看网页源代码可以发现，每组图片是这样子的




 <div class="boxgrid">


        <a href="big.php?i=1080652" title="Sci Fi Star Wars Kylo Ren HD Wallpaper | Background Image">


            <img class="" data-src="https://images7.alphacoders.com/108/thumb-350-1080652.jpg"


                alt="HD Wallpaper | Background Image ID:1080652"


                src="https://images7.alphacoders.com/108/thumb-350-1080652.jpg">


        </a>


    </div>




所以我们可以通过查找class="boxgrid"的所有div，然后取a中的href。


其中也有https://images7.alphacoders.com/108/thumb-350-1080652.jpg的网址，但是点进去看是小图片。我们需要下载大图片。


href还需要把基础地址加上才可以，把big.php?i=1080652变成https://wall.alphacoders.com/big.php?i=1080652


PS:可以使用F12,然后定位图片，然后选择图片找到对应的html代码就能找到规律






# -*- encoding=utf-8 -*-

import requests
from bs4 import BeautifulSoup


# 获取网页源代码
def get_html(url='https://wall.alphacoders.com/'):
    ret = requests.get(url)
    # 获取返回的状态 200表示请求成功
    print ret.status_code
    html = ret.text
    # 网页源代码
    # print html
    return html


# 获取链接
def get_photo_link(html):
    # 用来存放链接
    links = []
    soup = BeautifulSoup(html, features='lxml')
    # 找到所有class_='boxgrid'的div
    all_div = soup.find_all('div', class_='boxgrid')
    for div in all_div:
        # 取到href的值
        href = div.a.attrs['href']
        # 添加原地址组成真正url
        links.append('https://wall.alphacoders.com/' + href)
    return links


if __name__ == '__main__':
    html = get_html()
    links = get_photo_link(html)
    for link in links:
        print link


 






PS：BeautifulSoup使用可以参考https://cuiqingcai.com/1319.html


运行




https://wall.alphacoders.com/big.php?i=1080652
https://wall.alphacoders.com/big.php?i=1080635
https://wall.alphacoders.com/big.php?i=1080566
https://wall.alphacoders.com/big.php?i=1080405
https://wall.alphacoders.com/big.php?i=1080377
https://wall.alphacoders.com/big.php?i=1080376
https://wall.alphacoders.com/big.php?i=1080204
https://wall.alphacoders.com/big.php?i=1080025
https://wall.alphacoders.com/big.php?i=1079983
https://wall.alphacoders.com/big.php?i=1079969
https://wall.alphacoders.com/big.php?i=1079911
https://wall.alphacoders.com/big.php?i=1079838
https://wall.alphacoders.com/big.php?i=1079806
https://wall.alphacoders.com/big.php?i=1079738
https://wall.alphacoders.com/big.php?i=1079732
https://wall.alphacoders.com/big.php?i=1079731
https://wall.alphacoders.com/big.php?i=1079579
https://wall.alphacoders.com/big.php?i=1079360
https://wall.alphacoders.com/big.php?i=1079302
https://wall.alphacoders.com/big.php?i=1079174
https://wall.alphacoders.com/big.php?i=1079169
https://wall.alphacoders.com/big.php?i=1078982
https://wall.alphacoders.com/big.php?i=1078682
https://wall.alphacoders.com/big.php?i=1078534
https://wall.alphacoders.com/big.php?i=1078068
https://wall.alphacoders.com/big.php?i=1078043
https://wall.alphacoders.com/big.php?i=1077847
https://wall.alphacoders.com/big.php?i=1077792
https://wall.alphacoders.com/big.php?i=1077568
https://wall.alphacoders.com/big.php?i=1077530






3）4）获取xxx网页源代码(假设为yyy)以及找到yyy中图片链接（假设为zzz.jpg）




# -*- encoding=utf-8 -*-

import requests
from bs4 import BeautifulSoup


# 获取网页源代码
def get_html(url='https://wall.alphacoders.com/'):
    ret = requests.get(url)
    # 获取返回的状态 200表示请求成功
    print ret.status_code
    html = ret.text
    # 网页源代码
    # print html
    return html


# 获取链接
def get_photo_link(html):
    # 用来存放链接
    links = []
    soup = BeautifulSoup(html, features='lxml')
    # 找到所有class_='boxgrid'的div
    all_div = soup.find_all('div', class_='boxgrid')
    for div in all_div:
        # 取到href的值
        href = div.a.attrs['href']
        # 添加原地址组成真正url
        links.append('https://wall.alphacoders.com/' + href)
    return links


# 获取每一个链接的html以及找到对应图片的链接
def get_img_url(links):
    img_urls = []
    for link in links:
        html = get_html(link)
        img_soup = BeautifulSoup(html, features='lxml')
        all_img = img_soup.find_all('img', class_='main-content')
        for img in all_img:
            img_url = img.attrs['src']
            img_urls.append(img_url)
    return img_urls


if __name__ == '__main__':
    html = get_html()
    links = get_photo_link(html)
    img_urls = get_img_url(links)
    for img_url in img_urls:
        print img_url




运行




https://images7.alphacoders.com/108/thumb-1920-1080652.jpg
https://images7.alphacoders.com/108/thumb-1920-1080635.jpg
https://images8.alphacoders.com/108/thumb-1920-1080566.jpg
https://images6.alphacoders.com/108/thumb-1920-1080507.jpg
https://images.alphacoders.com/108/thumb-1920-1080405.png
https://images8.alphacoders.com/108/thumb-1920-1080377.jpg
https://images4.alphacoders.com/108/thumb-1920-1080376.jpg
https://images.alphacoders.com/108/thumb-1920-1080204.jpg
https://images4.alphacoders.com/108/thumb-1920-1080025.jpg
https://images8.alphacoders.com/107/thumb-1920-1079983.jpg
https://images6.alphacoders.com/107/thumb-1920-1079969.jpg
https://images4.alphacoders.com/107/thumb-1920-1079911.jpg
https://images6.alphacoders.com/107/thumb-1920-1079838.jpg
https://images6.alphacoders.com/107/thumb-1920-1079806.jpg
https://images8.alphacoders.com/107/thumb-1920-1079738.jpg
https://images.alphacoders.com/107/thumb-1920-1079732.jpg
https://images2.alphacoders.com/107/thumb-1920-1079731.jpg
https://images6.alphacoders.com/107/thumb-1920-1079579.jpg
https://images7.alphacoders.com/107/thumb-1920-1079360.jpg
https://images6.alphacoders.com/107/thumb-1920-1079302.jpg
https://images6.alphacoders.com/107/thumb-1920-1079174.jpg
https://images3.alphacoders.com/107/thumb-1920-1079169.jpg
https://images7.alphacoders.com/107/thumb-1920-1078982.png
https://images4.alphacoders.com/107/thumb-1920-1078682.jpg
https://images.alphacoders.com/107/thumb-1920-1078534.jpg
https://images4.alphacoders.com/107/thumb-1920-1078068.jpg
https://images5.alphacoders.com/107/thumb-1920-1078043.jpg
https://images3.alphacoders.com/107/thumb-1920-1077847.png
https://images2.alphacoders.com/107/thumb-1920-1077792.jpg
https://images4.alphacoders.com/107/thumb-1920-1077568.jpg




5）下载图片




# -*- encoding=utf-8 -*-
import os

import requests
from bs4 import BeautifulSoup


# 获取网页源代码
def get_html(url='https://wall.alphacoders.com/'):
    ret = requests.get(url)
    # 获取返回的状态 200表示请求成功
    print ret.status_code
    html = ret.text
    # 网页源代码
    # print html
    return html


# 获取链接
def get_photo_link(html):
    # 用来存放链接
    links = []
    soup = BeautifulSoup(html, features='lxml')
    # 找到所有class_='boxgrid'的div
    all_div = soup.find_all('div', class_='boxgrid')
    for div in all_div:
        # 取到href的值
        href = div.a.attrs['href']
        # 添加原地址组成真正url
        links.append('https://wall.alphacoders.com/' + href)
    return links


# 获取每一个链接的html以及找到对应图片的链接
def get_img_url(links):
    img_urls = []
    for link in links:
        html = get_html(link)
        img_soup = BeautifulSoup(html, features='lxml')
        all_img = img_soup.find_all('img', class_='main-content')
        for img in all_img:
            img_url = img.attrs['src']
            img_urls.append(img_url)
    return img_urls


# 文件夹不存在就创建
def create_folder(file_name):
    path = os.path.split(file_name)[0]
    if path != '' and not os.path.exists(path):
        os.makedirs(path)


# 下载图片
def download_img(img_urls):
    for img_url in img_urls:
        # 后缀名
        save_name_suffix = img_url[-3:]
        # 保存的名字
        save_name = 'ptotos/img.{}'.format(save_name_suffix)
        ret = requests.get(img_url)
        # 图片信息
        info = ret.content
        # 不存在文件就创建
        create_folder(save_name)
        # 二进制方式写入
        with open(save_name, 'wb') as f:
            f.write(info)


if __name__ == '__main__':
    html = get_html()
    links = get_photo_link(html)
    img_urls = get_img_url(links)
    download_img(img_urls)
    print 'End'




运行后




 6、遇到乱码处理以及添加请求头




# -*- coding: utf-8 -*-

import requests

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:57.0) Gecko/20100101 Firefox/57.0'}
url = 'http://sports.sina.com.cn/g/premierleague/index.shtml'
ret = requests.get(url, headers=headers)
print(ret.status_code)
ret.encoding = 'utf-8'
print(ret.text)




7、需要json数据时




# -*- coding: utf-8 -*-
import json

import requests

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:57.0) Gecko/20100101 Firefox/57.0'}
data = {'key1': 'value1', 'key2': 'value2'}
url = 'http://sports.sina.com.cn/g/premierleague/index.shtml'
ret = requests.get(url, headers=headers, data=json.dumps(data))
# ret = requests.post(url, json=data)  # 使用post需要json参数时
print(ret.status_code)
ret.encoding = 'utf-8'
print(ret.text)




 






            

            
posted @ 
2020-06-01 11:15 
南风丶轻语 
阅读(2009) 
评论(0) 
编辑 
收藏 
举报