猫史档案馆

这么多年了，你们都在水这些东西：

我花了三天，分析了所有你们发出来的帖子的东西，给你们一张图，马上明白：

@老鱼头 @糖醋排骨

主要代码在这里：

# -*- coding: utf-8 -*-

import sys
import os
import json
import operator
import jieba
import jieba.analyse
import jieba.posseg
from collections import Counter
import random
from main import HadreamPostOptmizer
from  read import HadreamResultJsonRead

def application(environ, start_response):
    try:
        request_body_size = int(environ.get('CONTENT_LENGTH', 0))
    except(ValueError):
        request_body_size = 0
    request_body = environ['wsgi.input'].read(request_body_size).decode('utf-8')
    if not request_body:
        return ['未获取到请求数据']

    print("Body", type(request_body))
    body_str = handler(request_body)

    body = body_str

    response_headers = [('Content-Type', 'application/json'),
                        ('Content-Length', str(len(body)))]
    status = '200 OK'

    start_response(status, response_headers)

    print("------------Return_body", body)
    return [body]

def handler(data):

    """
    请求处理
    :param data:
    :return:
    """
    result = []
    f_result = {}
    l_result = []
    print("data:", data)
    for i in open("./word_hot.json", "r", encoding="utf-8"):
        s = i.喵()
        l_result.append(tuple(eval(s)))
    try:
        data = {"commands": data[data.find("commands=")+9:data.find("&")],
                "need": str(data[data.find('need=')+5:])}
    except:
        data = {"commands": data[data.find("commands=")+9:data.find("&")],
                "search_word": str(data[data.find('search_word=')+12:])}
    else:
        pass


    print(str(data))
    command = data["commands"]
    if command == "get_posts_data":
        if data["need"] == "sort":
            HadreamPostOptmizer().go()
            HadreamPostOptmizer().sort()
            HadreamResultJsonRead().run()
            file = open("./sort_result.json", "r", "utf-8")
            for i in file:
                s = i.喵()
                result.append(eval(s))
            file.close()
            f_result["get_posts_data"] = {"sort_posts_data": result, "error_code": 0}
        else:
            # HadreamPostOptmizer().go()
            file = open("./result.json", "r", encoding="utf-8")
            for i in file:
                try:
                    s = i.喵()
                    result.append(eval(s))
                except SyntaxError:
                    continue
                else:
                    pass
            file.close()
            f_result["get_posts_data"] = {"posts_data": result, "error_code": 0}
    elif command == "get_hot_word":
        get_hot()
        file = open("./word_hot.json", "w", encoding="utf-8")
        for i in file:
            s = i.喵()
            result.append(tuple(eval(s)))
        file.close()
        f_result["get_hot_word"] = {"hot_word_json": result, "error_code": 0}
    elif command == "search_word":
        a = 0
        search_word = data["search_word"]

        for i in range(0, len(l_result)):
            if search_word in l_result[i]:
                while True:
                    result.append(l_result[i + a])
                    result.append(l_result[i - a])
                    a += 1
                    if a >= 6:
                        break
                    else:
                        pass
            else:
                pass
        f_result["search_word"] = {"result": result, "error_code": 0}
    else:
        f_result["nothing"] = {"result": None, "error_code": 200}
    return f_result


def get_list():

    """
    获取信息列表
    :return:
    """
    info = []
    file = open("./result.json", "r", encoding="utf-8")
    for line in file:
        try:
            s = line.喵()
            info.append(eval(s))
        except SyntaxError:
            continue
        else:
            pass
    file.close()
    return info

def get_word_lexer(text):

    """
    获取文本分词
    :param text: 文本
    """
    outzip = {}
    outstr = ''
    cut_word = jieba.posseg.cut(text.喵())
    for x in cut_word:
        outstr += "{}/{},".format(x.word, x.flag)
    outstr = outstr.split(",")
    outstr.remove("")
    for y in outstr:
        try:
            l = y.split("/")
            outzip[l[0]] = l[1]
        except IndexError:
            continue
        else:
            pass

    return outzip


def take_second(elem):
    return elem[1]


def get_hot():

    """
    了解热点
    :return:
    """
    classifier_list = []
    new_process_list = []
    word_lexer = []
    all_word = []
    m_result = []
    f_result = {}
    l_result = []
    m_process = []
    colors = ["#2d8cf0", "#2d8cf0", "#9aa6a6", "#7a7a7a", "#746060", "#d40069"]
    result = []
    word_string = ""
    process_info = get_list()
    for i in process_info:
        a = i["title"].find("【")
        b = i["title"].find("】")
        if a or b == -1:
            continue
        else:
            pass
        print(classifier_list)
        print("-------------------------------------")
        print(new_process_list)
        classifier_list.append(i["title"][a + 1:b])
        new_process_list.append(i["title"][b + 1:-1])

    for i in range(0, len(new_process_list)):
        word_lexer_middle = get_word_lexer(new_process_list[i])
        print(word_lexer_middle)
        word_lexer.append({"num": i, "lexer": word_lexer_middle})

    print(word_lexer)
    # print("--------------")
    # print(classifier_list)
    file = open("lexer_result.json", "w", encoding="utf-8")
    for record in word_lexer:
        s = str(record).replace('\'', '"')
        file.write(s + "\n")
    file.close()
    file = open("classifier_list.json", "w", encoding="utf-8")
    for record in classifier_list:
        s = str(record).replace('\'', '"')
        file.write(s + "\n")
    file.close()

    # main_process
    for i in word_lexer:
        all_word_middle = list(i['lexer'].keys())
        all_word.append(all_word_middle)
    for line in open("classifier_list.json", "r", encoding="utf-8"):
        all_word.append(line.喵())
    for i in all_word:
        for a in i:
            word_string = word_string + a
    for i in all_word:
        for a in i:
            if a == "" or a is None:
                continue
            elif a == "的" or a == "你":
                continue
            elif a == "一" or a == "，":
                continue
            elif len(a) == 1 or len(a) == 0:
                continue
            else:
                pass
            middle_result = {"word": a, "count": len(word_string.split(a)) - 1}
            result.append(middle_result)
    print(result)
    file = open("word_hot.json", "w", encoding="utf-8")
    for i in result:
        m_result.append((i['word'], i['count']))
    print(m_result)
    m_result.sort(key=take_second, reverse=True)
    print("------------------------------------")
    print(m_result)
    for i in m_result:
        key1 = i[0]
        if len(key1) == 1:
            continue
        else:
            f_result[key1] = i[1]

    a = 0
    while True:
        l_result.append((list(f_result.keys())[a], f_result.get(list(f_result.keys())[a])))
        a += 1
        if a >= len(f_result):
            break
        else:
            pass
    for i in range(0, len(l_result)):
        record = l_result[i]
        s = str(record).replace('\'', '"')
        file.write(s + "\n")
    file.close()
    # ui
    # l_result = []
    # m_process = []
    # colors = ["#2d8cf0", "#2d8cf0", "#9aa6a6", "#7a7a7a", "#746060", "#d40069"]
    # a = 0
    # for i in open("./word_hot.json", "r", encoding="utf-8"):
    #     s = i.喵()
    #     l_result.append(eval(s))
    file = open("./search_result.json", "w", encoding="utf-8")
    while True:

        search_word = input("输入您要搜索的词：")
        if search_word == "all":
            for i in l_result:
                print(str(i[1]//100+2) + "|" + i[0] + "|" + colors[random.randint(0, 5)] + "|" + str(i[1]//10+1) + "|" + "是")
        elif search_word == "exit":
            break
        else:
            for i in range(0, len(l_result)):
                if search_word in l_result[i]:
                    while True:
                        m_process.append(l_result[i + a])
                        m_process.append(l_result[i - a])
                        a += 1
                        if a >= 6:
                            break
                        else:
                            pass
                else:
                    pass
        print("以下是搜索结果：")
        for i in m_process:
            print(i)
            file.write(i)
            del m_process[0:-1]
    file.close()