正则表达式爬虫百度图片

最新推荐文章于 2024-03-30 11:02:52 发布

原创最新推荐文章于 2024-03-30 11:02:52 发布 · 913 阅读

1 ·

CC 4.0 BY-SA版权

文章标签：

#正则表达式 #爬虫 #百度

文章介绍了使用Python进行网页爬取，包括爬取单个图片的代码示例，以及如何爬取单个页面并下载所有图片，最后展示了爬取多个页面图片的方法，涉及requests库、正则表达式和BeautifulSoup解析。

从爬取单个照片到爬取单个页面，再是无限爬取！

一、爬取单个图片

import re
import requests

#定义url
url = 'https://img0.baidu.com/it/u=728444420,2020970780&fm=253&fmt=auto&app=138&f=JPEG?w=667&h=500'
#设置请求头
headers = {
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36",

}
#发送get请求
response = requests.get(url,headers=headers)
#变为bytes流数据
content = response.content
print(content)

#保存图片
with open('ORV.png','wb') as f: #
    f.write(content)

二、爬取单个页面图片

import re
import requests


#设置请求头
headers = {
    "User-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36",
    "Referer":"https://image.baidu.com/search/index?tn=baiduimage&ps=1&ct=201326592&lm=-1&cl=2&nc=1&ie=utf-8&dyTabStr=MCwzLDEsMiw2LDQsNSw4LDcsOQ%3D%3D&word=%E6%B1%BD%E8%BD%A6"
}
#url


url = 'https://image.baidu.com/search/index?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fm=result&fr=&sf=1&fmq=1699329412872_R&pv=&ic=&nc=1&z=&hd=&latest=&copyright=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&dyTabStr=MCwzLDEsMiw2LDQsNSw4LDcsOQ%3D%3D&ie=utf-8&sid=&word=越野汽车'

#发送get请求
response = requests.get(url,headers =headers)
#对数据解析
content = response.content.decode('utf8')
#print(content)
#数据提取# #
detail_urls = re.findall('"thumbURL":"(.*?)"',content,re.DOTALL)
print(detail_urls)
i=0
#图片下载
for detail_url in detail_urls:
    response = requests.get(detail_url,headers=headers)
    content = response.content
    path = r"E:\批量下载"    #保存路径
    with open(r'{}\{}.jpg'.format(path,i),'wb') as f:
        f.write(content)
    i+=1

三、爬取多个页面图片

import re
import requests
from urllib import error
from bs4 import BeautifulSoup
import os
num = 0
numPicture = 0
file = ''
List = []
def Find(url):
    global List
    print('正在检测图片总数，请稍等.....')
    t = 0
    i = 1
    s = 0
    while t < 2000:
        Url = url + str(t)
        try:
            Result = requests.get(Url, timeout=7)
        except BaseException:
            t = t + 60
            continue
        else:
            result = Result.text
            pic_url = re.findall('"objURL":"(.*?)",', result, re.S)  # 先利用正则表达式找到图片url
            s += len(pic_url)
            if len(pic_url) == 0:
                break
            else:
                List.append(pic_url)
                t = t + 60
    return s
def recommend(url):
    Re = []
    try:
        html = requests.get(url)
    except error.HTTPError as e:
        return
    else:
        html.encoding = 'utf-8'
        bsObj = BeautifulSoup(html.text, 'html.parser')
        div = bsObj.find('div', id='topRS')
        if div is not None:
            listA = div.findAll('a')
            for i in listA:
                if i is not None:
                    Re.append(i.get_text())
        return Re
def dowmloadPicture(html, keyword):
    global num
    # t =0
    pic_url = re.findall('"objURL":"(.*?)",', html, re.S)  # 先利用正则表达式找到图片url
    print('找到关键词:' + keyword + '的图片，即将开始下载图片...')
    for each in pic_url:
        print('正在下载第' + str(num + 1) + '张图片，图片地址:' + str(each))
        try:
            if each is not None:
                pic = requests.get(each, timeout=7)
            else:
                continue
        except BaseException:
            print('错误，当前图片无法下载')
            continue
        else:
            string = file + r'\\' + keyword + '_' + str(num) + '.jpg'
            fp = open(string, 'wb')
            fp.write(pic.content)
            fp.close()
            num += 1
        if num >= numPicture:
            return
if __name__ == '__main__':  # 主函数入口
    word = input("请输入搜索关键词(可以是人名，地名等): ")
    url = 'http://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word=' + word + '&pn='#翻页流的网址
    tot = Find(url)
    Recommend = recommend(url)  # 记录相关推荐
    print('经过检测%s类图片共有%d张' % (word, tot))
    numPicture = int(input('请输入想要下载的图片数量 '))
    file = input('请建立一个存储图片的文件夹，输入文件夹名称即可')
    y = os.path.exists(file)
    if y == 1:
        print('该文件已存在，请重新输入')
        file = input('请建立一个存储图片的文件夹，输入文件夹名称即可')
        os.mkdir(file)
    else:
        os.mkdir(file)
    t = 0
    tmp = url
    while t < numPicture:
        try:
            url = tmp + str(t)
            result = requests.get(url, timeout=10)
            print(url)
        except error.HTTPError as e:
            print('网络错误，请调整网络后重试')
            t = t + 60
        else:
            dowmloadPicture(result.text, word)
            t = t + 60
    print('当前搜索结束，感谢使用')
    print('猜你喜欢')
    for re in Recommend:
        print(re, end='  ')