osc/research/nuofang-db/nfm/mperson/avatar_parser.py

53 lines
2.0 KiB
Python
Raw Permalink Normal View History

2025-05-28 19:16:17 +08:00
import os
import re
import shutil
import pymysql
from lxml import etree
target_file_path = r"E:\yuxin\nuofang-data\person\webpage"
def trim_space(input_str):
result = re.sub(' {2,}', ' ', input_str.replace("\u3000", " "))
return result
def parse_avatar_info(current_selector):
img_url_info = current_selector.xpath("//table[@class='good-table table1']//img/@src")
img_url = "".join(img_url_info).strip()
return img_url
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('梅家樹_军政主官_全球军事态势情报数据库.html'):
count += 1
webpage_info = {}
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)
title_info = selector.xpath("//div[@class='good-info-box']/div[@class='top cls']/span/text()")
title = ''.join(title_info).strip()
url_info = selector.xpath('//ul[@class="osc-dropMenu"]/li[last()]/a/@href')[0]
page_url = url_info.replace("#", "")
avatar_url = parse_avatar_info(selector)
person_id = page_url[37:45]
if len(avatar_url) > 0:
avatar_file_name = avatar_url.split("/")[-1]
sql_update = "UPDATE nfm.m_person_page SET images = '{}' WHERE id = {} AND images IS NULL".format(
avatar_file_name, person_id)
shutil.copy(r"E:\yuxin\nuofang-data\person\webpage" + avatar_url[1:],
r"E:\yuxin\nuofang-data\person\person-avatar-2")
cursor.execute(sql_update)
print([person_id, avatar_file_name])
db.commit()
db.close()