使用python实现百度图片爬取（带关键词推荐）

使用python实现百度图片爬取（带关键词推荐）

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 < 100:
        Url = url + str(t)
        try:
            Result = requests.get(Url, timeout=7) #超时设置-136
        except BaseException:
            t = t + 60 #向后滑动60个图-一页60个图
            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-147
            s += len(pic_url)
            # print(s)
            if len(pic_url) == 0:
                break
            else:
                List.append(pic_url)
                t = t + 60


    print(s)
    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')
        # print(bsObj)
        div = bsObj.find('div', id='topRS') #定位
        if div is not None:
            listA = div.findAll('a')#定位a标签
            for i in listA:
                if i is not None:
                    Re.append(i.get_text())#取出标签内的推荐标题放入列表中
        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(pic_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)#-125-content是二进制形式（text打印的是str形式）
            fp.close()
            num += 1
        if num >= numPicture: #控制下载的图片数
            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): ")
    # add = 'http://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word=%E5%BC%A0%E5%A4%A9%E7%88%B1&pn=120'
    url = 'http://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word=' + word + '&pn='
    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) #超时设置
            # 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='  ')