kingsword-2

import os
import time
import random

import requests
import io
import hashlib

from PIL import Image
from selenium import webdriver

import signal

from glob import glob
import openpyxl

##############
# 参数设置
##############

# 要获取的图片数量
number_of_images = 9
GET_IMAGE_TIMEOUT = 2
SLEEP_BETWEEN_INTERACTIONS = 0.1
SLEEP_BEFORE_MORE = 5
IMAGE_QUALITY = 85

output_path = "C:\\Users\\Dr Lau\\Desktop\\KeywordImages\\"

# 获取已记录的术语。
dirs = glob(output_path + "*")
dirs = [dir.split("\\")[-1].replace("_", " ") for dir in dirs]

# 打开关键词调查表
workbook = openpyxl.load_workbook("C:\\Users\\Dr Lau\\Desktop\\关键词调查表.xlsx")
sheet = workbook.active

# 获取搜索关键词
search_terms = [row[0].value for row in sheet.iter_rows(min_row=2, max_col=1, values_only=True) if row[0].value and row[0].value not in dirs]

##########
# 抓取图片
##########

wd = webdriver.Chrome()

# 信用：
# https://stackoverflow.com/a/22348885
class timeout:
    def __init__(self, seconds=1, error_message="Timeout"):
        self.seconds = seconds
        self.error_message = error_message

    def handle_timeout(self, signum, frame):
        raise TimeoutError(self.error_message)

    def __enter__(self):
        signal.signal(signal.SIGALRM, self.handle_timeout)
        signal.alarm(self.seconds)

    def __exit__(self, type, value, traceback):
        signal.alarm(0)

def fetch_image_urls(
    query: str,
    max_links_to_fetch: int,
    wd: webdriver,
    sleep_between_interactions: int = 1,
):
    # ... 这里是抓取图片链接的函数 ...

def persist_image(folder_path: str, url: str, filename: str):
    # ... 这里是保存图片的函数 ...

def search_and_download(search_term: str, target_path="./images", number_images=5):
    # ... 这里是搜索和下载图片的函数 ...

for term in search_terms:
    search_and_download(term, output_path, number_of_images)