osc/research/nuofang-db/nfm/mbase/image_parser.py

50 lines
2.1 KiB
Python
Raw Normal View History

2025-05-28 19:16:17 +08:00
import json
import os
import pymysql
from lxml import etree
from nfm.mbase.page_parser import parse_base_info
target_file_path = r"E:/yuxin/nuofang-data/base/webpage"
image_path = r"E:/yuxin/nuofang-data/base/images"
full_image_path = r"E:/yuxin/nuofang-data/base/full_images"
if __name__ == '__main__':
count = 0
db = pymysql.connect(host='39.101.194.63', port=23306,
user='root', passwd='passok123A', db='nfm', charset='utf8mb4')
cursor = db.cursor()
for _path in os.listdir(target_file_path):
if _path.endswith('.html'):
# if _path.endswith('埃尔门多夫-理查森堡联合基地_综合类设施_全球军事态势情报数据库.html'):
count += 1
target_file = open(target_file_path + '\\' + _path, mode='r', encoding='utf-8')
html_content = target_file.read().replace('\n', '')
target_file.close()
selector = etree.HTML(html_content)
base_info = parse_base_info(selector, "")
internal_id = base_info['内部编号']
img_uris = selector.xpath("//div[@id='det_right']//a[@class='img']/img/@src")
full_images_urls = selector.xpath("//div[@id='det_right']//a[@class='img']/@href")
images = []
image = ''
# print("[No. {}] {}: {} images".format(count, _path[:-23], len(full_images_urls)))
for url in full_images_urls:
if url.startswith("http"):
print(url)
img_file_name = url.split("/")[-1]
images.append(img_file_name)
# for uri in img_uris:
# if uri.startswith("./"):
# img_file_name = uri.split("/")[-1]
# images.append(img_file_name)
# shutil.copy(target_file_path + uri[1:], image_path)
# if len(images) > 0:
# image = images[0]
sql_update = "UPDATE nfm.m_base_page SET full_size_images = '{}' WHERE internal_id = '{}'".format(
json.dumps(images, ensure_ascii=False), internal_id)
cursor.execute(sql_update)
db.commit()
db.close()