爬蟲百度圖片

轉載一個下載百度圖片還不錯的程序，忘了從哪看的了，放在這吧 以後用了翻一番

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('正在檢測圖片總數，請稍等.....')
    t = 0
    i = 1
    s = 0
    while t < 1000:
        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)  # 先利用正則表達式找到圖片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,word):
    global num
    # t =0
    pic_url = re.findall('"objURL":"(.*?)",', html, re.S)  # 先利用正則表達式找到圖片url
    print('找到關鍵詞:' + keyword + '的圖片，即將開始下載圖片...')
    for each in pic_url:
        print('正在下載第' + str(num + 1) + '張圖片，圖片地址:' + str(each))
        try:
            if each is not None:
                pic = requests.get(each, timeout=7)
            else:
                continue
        except BaseException:
            print('錯誤，當前圖片無法下載')
            continue
        else:
            string = file + r'\\' + word + '_' + str(num) + '.jpg'
            fp = open(string, 'wb')
            fp.write(pic.content)
            fp.close()
            num += 1
        if num >= numPicture:
            return


if __name__ == '__main__':  # 主函數入口
    keyword = input("請輸入搜索關鍵詞(可以是人名，地名等): ")
    word = input("請輸入保存名: ")
    # 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=' + keyword + '&pn='
    tot = Find(url)
    Recommend = recommend(url)  # 記錄相關推薦
    print('經過檢測%s類圖片共有%d張' % (keyword, tot))
    numPicture = int(input('請輸入想要下載的圖片數量 '))
    file = input('請建立一個存儲圖片的文件夾，輸入文件夾名稱即可')
    y = os.path.exists(file)
    if y == 1:
        print('該文件已存在，請重新輸入')
        file = input('請建立一個存儲圖片的文件夾，)輸入文件夾名稱即可')
        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('網絡錯誤，請調整網絡後重試')
            t = t + 60
        else:
            dowmloadPicture(result.text, keyword, word)
            t = t + 60

    print('當前搜索結束，感謝使用')
    print('猜你喜歡')
    for re in Recommend:
        print(re, end='  ')