淘宝商品html--网页结构

淘宝商品html--网页结构

本篇爬虫紧接上一篇关于 泸州老窖 的爬虫随笔：

import re
import json

def get_space_end(level):
    return '  ' * level + '-'

def get_space_expand(level):
    return '  ' * level + '+'

def find_keys(targets, level):
    """
    设置递归函数，输入是一个字典，level是级别，最后返回的是字典的结构；
    :param targets: dict
    :param level: num
    :return: 返回字典的keys结构
    """
    keys = iter(targets)

    for each in keys:
        if type(targets[each]) is not dict:
            with open("keys.txt", "a+", encoding="utf-8") as file:
                file.write(get_space_end(level) + each + '\n')
            print(get_space_end(level) + each)
        else:
            next_level = level + 1
            with open("keys.txt", "a+", encoding="utf-8") as file:
                file.write(get_space_expand(level) + each + '\n')
            print(get_space_expand(level) + each)
            find_keys(targets[each], next_level)

def main():
    with open("items.txt", "r", encoding="utf-8") as file1:
        g_page_config = re.search(r"g_page_config = (.*?);\n", file1.read())
        page_config_json = json.loads(g_page_config.group(1))
        find_keys(page_config_json, 1)

if __name__ == "__main__":
    main()