import re
import uuid

import requests
import random
from lxml import html
from UserAgent import user_agent_pool
import pymysql

class ChineseMedicineSpider(object):
    def __init__(self):
        self.headers = {'User-Agent': random.choice(user_agent_pool)}
    # 启动爬虫
    def run_spider(self):
        pages = int(input('请输入需要爬取的页数：（小于或等于45）'))
        if pages >= 0 and pages <= 45:
            print('爬虫开始运行！！！')
            self.get_chinese_medicine(pages)
            print('爬虫运行结束！！！')
        else:
            print("输入无效！！！")

    def get_chinese_medicine(self, pages):
        medList = []
        for page in range(46, pages + 46):
            url = f'http://www.zhongyoo.com/name/page_{page}.html'
            # print(url)
            resp = requests.get(url, self.headers)
            if resp.status_code == 200:
                # print(resp.content.decode('gbk'))
                tree = html.fromstring(resp.content.decode('gbk'))
                zy_name_list = tree.xpath('//div[@class="sp"]/span/a/img/@alt')  # 匹配到中药材的名字
                zy_imge_list = tree.xpath('//div[@class="sp"]/span/a/img/@src')  # 匹配到中药材的图片url
                zy_info_list = tree.xpath('//div[@class="sp"]/span/a/@href')  # 选取该页全部的中药的详情页url
                i = 0
                for zy_name in zy_name_list:
                    chinese_medicine = {}  # 创建一个存放中药材信息的字典
                    chinese_medicine['name'] = zy_name
                    print(zy_name)
                    imge_url = zy_imge_list[i]
                    print(zy_imge_list[i])
                    # self.get_chinese_medicine_imge(imge_url, chinese_medicine)
                    info_url = zy_info_list[i]
                    self.get_chinese_medicine_info(info_url, chinese_medicine)
                    medicine_info = {}
                    i += 1
                    for key, value in chinese_medicine.items():
                        print(f'Key: {key}, Value: {value}')
                        if key == 'info':
                            medicine_info['alias'] = ''
                            medicine_info['english'] = ''
                            medicine_info['harvest'] = ''
                            medicine_info['origin'] = ''
                            medicine_info['morphology'] = ''
                            medicine_info['parts'] = ''
                            medicine_info['character'] = ''
                            medicine_info['famt'] = ''
                            medicine_info['efficacy'] = ''
                            medicine_info['clinical'] = ''
                            medicine_info['pharmacological'] = ''
                            medicine_info['bases'] = ''
                            medicine_info['Usage'] = ''
                            for line in value.split('\n'):
                                if "【中药名】" in line or "【正名】" in line or "【药名】" in line  :
                                    new_str = line.replace("【中药名】", "").replace("【正名】", "").replace("【药名】", "")
                                    sp = new_str.split()
                                    medicine_info['name'] = sp[0]
                                    if len(sp) > 1:
                                        medicine_info['pinyin'] = sp[1]
                                    else:
                                        medicine_info['pinyin'] = ''
                                if "【别名】" in line:
                                    medicine_info['alias'] = line.replace("【别名】", "")  .replace("【别名】", "")
                                if "【英文名】" in line or "【外语名】" in line:
                                    medicine_info['english'] = line.replace("【外语名】", "").replace("【英文名】", "")
                                if "【药用部位】" in line:
                                    medicine_info['parts'] = line   # .replace("【药用部位】", "")
                                if "【植物形态】" in line:
                                    medicine_info['morphology'] = line  # .replace("【植物形态】", "")
                                if "【产地分布】" in line:
                                    medicine_info['origin'] = line  # .replace("【产地分布】", "")
                                if "【采收加工】" in line:
                                    medicine_info['harvest'] = line  # .replace("【采收加工】", "")
                                if "【药材性状】" in line:
                                    medicine_info['character'] = line  # .replace("【药材性状】", "")
                                if "【性味归经】" in line:
                                    medicine_info['famt'] = line  # .replace("【性味归经】", "")
                                if "【功效与作用】" in line:
                                    medicine_info['efficacy'] = line  # .replace("【功效与作用】", "")
                                if "【临床应用】" in line:
                                    medicine_info['clinical'] = line  # .replace("【临床应用】", "")
                                if "【药理研究】" in line:
                                    medicine_info['pharmacological'] = line  # .replace("【药理研究】", "")
                                if "【主要成分】" in line or "【化学成分】" in line:
                                    medicine_info['bases'] = line  # .replace("【主要成分】", "").replace("【化学成分】", "")
                                if "【使用禁忌】" in line:
                                    medicine_info['Usage'] = line  # .replace("【使用禁忌】", "")
                            # 建立与MySQL服务器的连接
                            conn = pymysql.connect(host='192.168.2.6', user='root', password='123456',
                                                   database='herb')
                            cursor = conn.cursor()
                            uuid_val = uuid.uuid4()
                            try:
                                selectSql = "select * from dry_herb_info where name = '" + medicine_info['name'] + "'"
                                cursor.execute(selectSql)
                                res = cursor.fetchone()
                                print(res)
                                if res == None:
                                    # SQL语句，将数据插入到表格中
                                    sql = "INSERT INTO dry_herb_info (id, name, pinyin, alias, english, parts, morphology, origin, harvest, character_drug, famt, efficacy, clinical, pharmacological, bases, usage_taboo) VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s,%s, %s,%s,%s,%s,%s,%s)"
                                    data = (uuid_val,medicine_info['name'],medicine_info['pinyin'],medicine_info['alias'],medicine_info['english'],
                                            medicine_info['parts'],medicine_info['morphology'],medicine_info['origin'],medicine_info['harvest'],medicine_info['character'],
                                            medicine_info['famt'],medicine_info['efficacy'],medicine_info['clinical'],medicine_info['pharmacological'],medicine_info['bases'],medicine_info['Usage'])
                                    # 执行SQL语句
                                    cursor.execute(sql,data)
                                    # 提交事务
                                    conn.commit()
                            except Exception as e:
                                print("Error occurred while inserting data into MySQL table.")
                                print(e)
                            finally:
                                # 关闭游标和连接
                                cursor.close()
                                conn.close()
                    medList.append(medicine_info)
            else:
                print("响应结果为空")
    def get_chinese_medicine_info(self, info_url, chinese_medicine):
        # 发送请求
        try:
            resp = requests.get(info_url, self.headers).content.decode('gbk')
            # 匹配<p></p>和<p></p>中间的全部内容
            pattern = r'<p></p>([\s\S]*?)<p></p>'
            match = re.search(pattern, resp)
            if match:
                # print(match.group(1))
                # 正则表达式 < [ ^ >]+ > 匹配HTML标签及其内容，并将其替换为空字符串，从而实现了去除HTML标签和标签中内容的效果
                text = re.sub(r"<[^>]+>", "", match.group(1))
                # 去除【前的空格
                text = re.sub(r"\s+【", "\n【", text)
                # 去除开头空白行
                text = re.sub(r"^\s*", "", text)
                # 去除相关推荐文章
                text = re.sub(r"相关推荐文章.*", "", text, flags=re.DOTALL)
                # 去除结尾空白行
                info = re.sub(r"\s*$", "", text)
                # 把爬取到的详细信息存入到字典
                chinese_medicine['info'] = info
            else:
                chinese_medicine['info'] = "暂无详细信息,请等待管理员添加!"
        except Exception as e:
            pass
if __name__ == '__main__':
    zy = ChineseMedicineSpider()
    zy.run_spider()