Python——百度图片爬虫

import re
import requests
from urllib import error
from bs4 import BeautifulSoup
import random
import os

num = 0
numPicture = 0
file = ''
List = []
headers = [
    "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36",
    "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:30.0) Gecko/20100101 Firefox/30.0",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.75.14 (KHTML, like Gecko) Version/7.0.3 Safari/537.75.14",
    "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; Win64; x64; Trident/6.0)",
    'Mozilla/5.0 (Windows; U; Windows NT 5.1; it; rv:1.8.1.11) Gecko/20071127 Firefox/2.0.0.11',
    'Opera/9.25 (Windows NT 5.1; U; en)',
    'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)',
    'Mozilla/5.0 (compatible; Konqueror/3.5; Linux) KHTML/3.5.5 (like Gecko) (Kubuntu)',
    'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.0.12) Gecko/20070731 Ubuntu/dapper-security Firefox/1.5.0.12',
    'Lynx/2.8.5rel.1 libwww-FM/2.14 SSL-MM/1.4.1 GNUTLS/1.2.9',
    "Mozilla/5.0 (X11; Linux i686) AppleWebKit/535.7 (KHTML, like Gecko) Ubuntu/11.04 Chromium/16.0.912.77 Chrome/16.0.912.77 Safari/535.7",
    "Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:10.0) Gecko/20100101 Firefox/10.0 "
]
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 < 1000:
        Url = url + str(t)
        try:
            header = {
                "User-Agent": random.choice(headers)  # 随机选择请求头，模拟不同的浏览器
            }
            Result = requests.get(Url, headers=header, 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:
        header = {
            "User-Agent": random.choice(headers)  # 随机选择请求头，模拟不同的浏览器
        }
        html = requests.get(url,headers=header)
    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:
                header = {
                    "User-Agent": random.choice(headers)  # 随机选择请求头，模拟不同的浏览器
                }
                pic = requests.get(each, headers=header,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
    tm = int(input('请输入每类图片的下载数量 '))
    numPicture = tm
    line_list = ['py', 'python']
    '''
    with open('./name.txt', encoding='utf-8') as file:
        line_list = [k.strip() for k in file.readlines()]  # 用 strip()移除末尾的空格

    '''
    for word in line_list:
        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))
        file = word + '文件'
        y = os.path.exists(file)
        if y == 1:
            print('该文件已存在，请重新输入')
            file = word + '文件夹2'
            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
        numPicture = numPicture + tm

    print('当前搜索结束，感谢使用')

参考文章

https://blog.csdn.net/qq_40774175/article/details/81273198