# 抓取百度貼吧某個(gè)帖子里的所有圖片
import requests
import time
import threading
import queue
from bs4 import BeautifulSoup
import chardet
import os

tiezi_url = "https://tieba.baidu.com/p/5522091060"
headers = {
    'Host': 'tieba.baidu.com',
    'User-Agent': 'User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KH'
                  'TML, like Gecko) Chrome/90.0.4430.212 Safari/537.36',
}
pic_save_dir = 'tiezi_pic/'
if not os.path.exists(pic_save_dir):  # 判斷文件夾是否存在，不存在就創(chuàng)建
    os.makedirs(pic_save_dir)

pic_urls_file = 'tiezi_pic_urls.txt'
download_q = queue.Queue()  # 下載隊(duì)列


# 獲得頁數(shù)
def get_page_count():
    try:
        resp = requests.get(tiezi_url, headers=headers, timeout=5)
        if resp is not None:
            resp.encoding = chardet.detect(resp.content)['encoding']
            html = resp.text
            soup = BeautifulSoup(html, 'lxml')
            a_s = soup.find("ul", attrs={'class': 'l_posts_num'}).findAll("a")
            for a in a_s:
                if a.get_text() == '尾頁':
                    return a['href'].split('=')[1]
    except Exception as e:
        print(str(e))


# 下載線程
class PicSpider(threading.Thread):
    def __init__(self, t_name, func):
        self.func = func
        threading.Thread.__init__(self, name=t_name)

    def run(self):
        self.func()


# 獲得每頁里的所有圖片URL
def get_pics(count):
    params = {
        'pn': count,
        'ajax': '1',
        't': int(time.time())
    }
    try:
        resp = requests.get(tiezi_url, headers=headers, timeout=5, params=params)
        if resp is not None:
            resp.encoding = chardet.detect(resp.content)['encoding']
            html = resp.text
            soup = BeautifulSoup(html, 'lxml')
            imgs = soup.findAll('img', attrs={'class': 'BDE_Image'})
            for img in imgs:
                print(img['src'])
                with open(pic_urls_file, 'a') as fout:
                    fout.write(img['src'])
                    fout.write('\n')
            return None
    except Exception:
        pass


# 下載線程調(diào)用的方法
def down_pics():
    global download_q
    while not download_q.empty():
        data = download_q.get()
        download_pic(data)
        download_q.task_done()


# 下載調(diào)用的方法
def download_pic(img_url):
    try:
        resp = requests.get(img_url, headers=headers, timeout=10)
        if resp.status_code == 200:
            print("下載圖片:" + img_url)
            pic_name = img_url.split("/")[-1][0:-1]
            with open(pic_save_dir + pic_name, "wb+") as f:
                f.write(resp.content)

    except Exception as e:
        print(e)


if __name__ == '__main__':
    print("檢索判斷鏈接文件是否存在：")
    if not os.path.exists(pic_urls_file):
        print("不存在，開始解析帖子...")
        page_count = get_page_count()
        if page_count is not None:
            headers['X-Requested-With'] = 'XMLHttpRequest'
            for page in range(1, int(page_count) + 1):
                get_pics(page)
        print("鏈接已解析完畢！")
        headers.pop('X-Requested-With')
    else:
        print("存在")
    print("開始下載圖片~~~~")
    headers['Host'] = 'imgsa.baidu.com'
    fo = open(pic_urls_file, "r")
    pic_list = fo.readlines()

    threads = []
    for pic in pic_list:
        download_q.put(pic)
    for i in range(0, len(pic_list)):
        t = PicSpider(t_name='線程' + str(i), func=down_pics)
        t.daemon = True
        t.start()
        threads.append(t)
    download_q.join()
    for t in threads:
        t.join()
    print("圖片下載完畢")

pip install baidu-aip 

from aip import AipOcr

# 新建一個(gè)AipOcr對象
config = {
    'appId': '填寫自己的appId',
    'apiKey': '填寫自己的apiKey',
    'secretKey': '填寫自己的secretKey'
}
client = AipOcr(**config)


# 識別圖片里的文字
def img_to_str(image_path):
    # 讀取圖片
    with open(image_path, 'rb') as fp:
        image = fp.read()

        # 調(diào)用通用文字識別, 圖片參數(shù)為本地圖片
    result = client.basicGeneral(image)
    # 返回拼接結(jié)果
    if 'words_result' in result:
        return '\n'.join([w['words'] for w in result['words_result']])


if __name__ == '__main__':
    print(img_to_str('tiezi_pic/5c0ddb1e4134970aebd593e29ecad1c8a5865dbd.jpg'))

{'words_result': [{'words': 'o。o'}, {'words': '6226-16:59'}, {'words': '絕望jpg'}], 'log_id': 1393611954748129280, 'words_result_num': 3}
o。o
6226-16:59
絕望jpg

# 識別圖片文字，批量命名圖片文字

import os
from aip import AipOcr
import re
import datetime

# 新建一個(gè)AipOcr對象
config = {
    'appId': '填寫自己的appId',
    'apiKey': '填寫自己的apiKey',
    'secretKey': '填寫自己的secretKey'
}
client = AipOcr(**config)

pic_dir = r"tiezi_pic/"


# 讀取圖片
def get_file_content(file_path):
    with open(file_path, 'rb') as fp:
        return fp.read()


# 識別圖片里的文字
def img_to_str(image_path):
    image = get_file_content(image_path)
    # 調(diào)用通用文字識別, 圖片參數(shù)為本地圖片
    result = client.basicGeneral(image)
    # 結(jié)果拼接返回
    words_list = []
    if 'words_result' in result:
        if len(result['words_result']) > 0:
            for w in result['words_result']:
                words_list.append(w['words'])
            file_name = get_longest_str(words_list)
            print(file_name)
            file_dir_name = pic_dir + str(file_name).replace("/", "") + '.jpg'
            if os.path.exists(file_dir_name):  # 處理文件重名問題
                sec = datetime.datetime.now().microsecond  # 獲取當(dāng)前毫秒時(shí)值
                file_dir_name = pic_dir + str(file_name).replace("/", "") + str(sec) + '.jpg'
            try:
                os.rename(image_path, file_dir_name)
            except Exception:
                print(" 重命名失?。?, image_path, " => ", file_name)


# 獲取字符串列表中最長的字符串
def get_longest_str(str_list):
    pat = re.compile(r'[\u4e00-\u9fa5A-Za-z]+')
    str = max(str_list, key=hanzi_len)
    result = pat.findall(str)
    return ''.join(result)


def hanzi_len(item):
    pat = re.compile(r'[\u4e00-\u9fa5]+')
    sum = 0
    for i in item:
        if pat.search(i):
            sum += 1
    return sum


# 遍歷某個(gè)文件夾下所有圖片
def query_picture(dir_path):
    pic_path_list = []
    for filename in os.listdir(dir_path):
        pic_path_list.append(dir_path + filename)
    return pic_path_list


if __name__ == '__main__':
    pic_list = query_picture(pic_dir)
    if len(pic_list) > 0:
        for i in pic_list:
            img_to_str(i)