Python爬取美女图片

目标分析：
1、对主页发送请求
2、使用xpath解析数据
3、提取主页中每个详情页的url
4、for循环遍历对每个详情页的url发送请求
5、解析每个详情页的url数据
6、正则提取每个详情页的url数据中的图片地址
7、保存数据

 1、对主页发送请求

import requests
from lxml import etree
import re

# 主页url
url = 'https://www.yituyu.com/w/4/'

# 模拟浏览器
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.84 Safari/537.36'
}
# 1、对主页发送请求
response = requests.get(url, headers=headers)

2、使用xpath解析数据

# 2、使用xpath解析数据
data = etree.HTML(html)

# 3、提取主页中每个详情页的url
data_url = data.xpath('/html/body/div[3]/div[3]/ul/li/div/a/@href')
# print(data_url)

 3、提取主页中每个详情页的url    4、for循环遍历对每个详情页的url发送请求   5、解析每个详情页的url数据

for url_ in data_url:
    url_str = ''.join(url_)
    # print(url_str)
    response_2 = requests.get(url_str, headers=headers).text
    # print(response_2)

6、正则提取每个详情页的url数据中的图片地址

    # 提取图片地址
    url_re = re.findall('<img class="lazy t0" data-src="(.*?)".*?', response_2, re.S)
    # print(url_re)

    # 提取图片名
    name_re = re.findall('<img class="lazy t0".*?alt="(.*?)".*?>.*?', response_2, re.S)
    # print(name_re)

7、保存数据

    for url_name in zip(name_re, url_re):
        resp_3 = requests.get(url_name[1], headers=headers).content
        name_ = url_name[0]
        i = i + 1
        name_1 = name_ + f'{i}'

        # print(name_1)
        with open(f'./tupian/{name_1}.jpg', 'wb') as f:
            f.write(resp_3)
            print(name_1 + "   ------下载完成")

 完整代码：

import requests
from lxml import etree
import re

# 主页url
url = 'https://www.yituyu.com/w/4/'

# 模拟浏览器
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.84 Safari/537.36'
}
# 1、对主页发送请求
response = requests.get(url, headers=headers)
html = response.text

# 2、使用xpath解析数据
data = etree.HTML(html)

# 3、提取主页中每个详情页的url
data_url = data.xpath('/html/body/div[3]/div[3]/ul/li/div/a/@href')
# print(data_url)
for url_ in data_url:
    url_str = ''.join(url_)
    # print(url_str)
    response_2 = requests.get(url_str, headers=headers).text
    # print(response_2)

    # 提取图片地址
    url_re = re.findall('<img class="lazy t0" data-src="(.*?)".*?', response_2, re.S)
    # print(url_re)

    # 提取图片名
    name_re = re.findall('<img class="lazy t0".*?alt="(.*?)".*?>.*?', response_2, re.S)
    # print(name_re)
    i = 0
    for url_name in zip(name_re, url_re):
        resp_3 = requests.get(url_name[1], headers=headers).content
        name_ = url_name[0]
        i = i + 1
        name_1 = name_ + f'{i}'

        # print(name_1)
        with open(f'./tupian/{name_1}.jpg', 'wb') as f:
            f.write(resp_3)
            print(name_1 + "   ------下载完成")