爬虫学习案例3

爬取美女图片

优美图库地址

一页图片

安装依赖库文件
复制代码
pip install selenium requests beautifulsoup4


import time
import requests
import random
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options
# 设置Chrome选项
chrome_options = Options()
chrome_options.add_argument("--headless")  # 无头模式,不打开浏览器窗口
chrome_options.add_argument("--disable-gpu")
chrome_options.add_argument("--no-sandbox")

# 设置ChromeDriver路径
service = Service('D:envpython3chromedriver.exe')
url = 'https://www.umei.cc/touxiangtupian/nvshengtouxiang/'
baseUrl = "https://www.umei.cc"
# 初始化WebDriver
driver = webdriver.Chrome(service=service, options=chrome_options)
driver.get(url)
time.sleep(random.uniform(5, 10))  # 等待页面加载
html = driver.page_source # 原页面
soup = BeautifulSoup(html, 'html.parser')
# print(soup)
# BeautifulSoup分析提取元素
divList = soup.find_all("div",class_= "item masonry_brick")
# print(divList)
# 一个美女信息
for divItem in divList:
    linkImage = divItem.find("div",class_ = "item_t").find("div",class_ = "img").find("a")["href"]
    linkImage = baseUrl + linkImage
    # 拿去子页面的大图
    driver.get(linkImage)
    time.sleep(random.uniform(5, 10))
    html = driver.page_source
    sonSoup = BeautifulSoup(html, 'html.parser')
    imgUrl = sonSoup.find("div",class_ = "tsmaincont-main-cont-txt").find("img")["src"]
    print(f"准备下载图片{imgUrl}")
    # 下载图片
    img_response = requests.get(imgUrl)
    img_name = imgUrl.split('/')[-1]
    with open("img"+img_name, "wb") as f:
        f.write(img_response.content)
    print(f"图片{img_name}下载完成")
print("第一页图片全部下载到当前目录了.....")
driver.quit()  # 关闭浏览器
爬取多页
复制代码
import time
import requests
import random
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options
# 设置Chrome选项
chrome_options = Options()
chrome_options.add_argument("--headless")  # 无头模式,不打开浏览器窗口
chrome_options.add_argument("--disable-gpu")
chrome_options.add_argument("--no-sandbox")

# 设置ChromeDriver路径
service = Service('D:envpython3chromedriver.exe')
url = 'https://www.umei.cc/touxiangtupian/nvshengtouxiang/'
baseUrl = "https://www.umei.cc"
# 初始化WebDriver
driver = webdriver.Chrome(service=service, options=chrome_options)

def getImage(url,page):
    driver.get(url)
    print(f"正在爬取第{page}页图片资源源...")
    print(url)
    time.sleep(random.uniform(5, 10))  # 等待页面加载
    html = driver.page_source # 原页面
    soup = BeautifulSoup(html, 'html.parser')
    # BeautifulSoup分析提取元素
    divList = soup.find_all("div",class_= "item masonry_brick")
    for divItem in divList:
        linkImage = divItem.find("div",class_ = "item_t").find("div",class_ = "img").find("a")["href"]
        linkImage = baseUrl + linkImage
        # 拿取子页面的大图
        driver.get(linkImage)
        time.sleep(random.uniform(5, 10))
        html = driver.page_source
        sonSoup = BeautifulSoup(html, 'html.parser')
        imgUrl = sonSoup.find("div",class_ = "tsmaincont-main-cont-txt").find("img")["src"]
        print(f"准备下载图片{imgUrl}")
        # 下载图片
        img_response = requests.get(imgUrl)
        img_name = imgUrl.split('/')[-1]
        with open("img"+img_name, "wb") as f:
            f.write(img_response.content)
        print(f"图片{img_name}下载完成")
    print(f"第{page}页图片全部下载到当前img目录了.....")

# 爬取1-10页
# 控制爬取的页面数
for page in range(1, 11):
    if page == 1:
        getImage(url,page)
    else:
        pageUrl = f"{url}index_{page}.htm"
        getImage(pageUrl,page)
driver.quit()  # 关闭浏览器
相关推荐
2601_9679801129 分钟前
Flask Web 应用
python·flask·web开发·环境变量·虚拟环境
aifannihao1 小时前
ß 大写变 SS:用 Python 算清 Ruby2Shell 的缓冲区账本
python·安全·标准库·缓冲区溢出·字符串编码
liwulin05061 小时前
【OLLAMA】调用SKILL的通用ReAct
python
郝学胜-神的一滴2 小时前
Effective Python 条款36:优雅拼装迭代器与生成器
开发语言·数据结构·人工智能·python·numpy·scikit-learn
Norna3 小时前
Git 给路径加了引号,这个文件就从 review 里消失了
python
Z21-X3 小时前
云原生运维学习笔记:Kubernetes Volume 与 Secret 实验
运维·笔记·学习·云原生·kubernetes
wuyk5553 小时前
Python办公自动化-第04讲-批量新建Excel
开发语言·python·excel
wuyk5553 小时前
Spider-第20讲-综合实战可上线爬虫
大数据·爬虫·python·elasticsearch
JonaHu4 小时前
关键词排名突然消失?用 Python、SQLite 和 SERP API 搭一套可解释的 SEO 监控
python·sqlite·seo·serp api