spider/SpiderWebsite/demo/views.py

import random
import re

import jieba as jieba
import pymysql
from django.http import HttpResponse
from django.shortcuts import render
from django.views.decorators.clickjacking import xframe_options_sameorigin
from jinja2 import Environment, FileSystemLoader
from pyecharts.faker import Faker
from pyecharts.globals import CurrentConfig
from django.http import HttpResponse
from pyecharts import options as opts
from pyecharts.charts import Bar, Pie
from pyecharts.charts import WordCloud


CurrentConfig.GLOBAL_ENV = Environment(loader=FileSystemLoader("./demo/templates"))

def home(request):
    return render(request, 'home.html')


@xframe_options_sameorigin
def page_views(request, page):
    # 解析路由，找到返回的页面
    # current = request.path.split('/')[-1]
    # return render(request, current + '.html')
    return render(request, 'page' + str(page) + '.html')


def table_one(request):
    x = []
    xaxis = []
    yaxis = []

    conn = pymysql.connect(host='120.79.165.140',
                            user='kino',
                            passwd="student",
                            db='python_web_spider_DB')
    cur = conn.cursor()

    sql1 = "SELECT distinct 规格 from wh_xinfadi"
    sql2 = "SELECT 规格,count(distinct 蔬菜种类) from wh_xinfadi group BY 规格"
    cur.execute(sql1)

    for sp in cur:
        init = str(sp)
        if '\'' in init:
            this_kind = init.split('\'')[1]
        else:
            this_kind = init
        if re.match(r'^([\u4e00-\u9fa5]+类)$', this_kind):
            x.append(this_kind)

    cur.execute(sql2)
    for it in cur:
        if it[0] in x:
            xaxis.append(it[0])
            yaxis.append(it[1])
    c = (
        Bar()
        .extend_axis(xaxis)
        .add_xaxis(xaxis)
        .add_yaxis('北京新发地菜市', yaxis,)
        .set_global_opts(
            title_opts=opts.TitleOpts(
                title="北京新发地菜市场",
                subtitle="产品种类分析"
            ),
            datazoom_opts=opts.DataZoomOpts(),
        )
    )
    # conn.commit()  # 记得提交
    cur.close()
    conn.close()
    return HttpResponse(c.render_embed('北京新发地菜市场产品种类分析.html'))


def pie_views(requset):
    data = [
        ['1990年及以前', 0],
        ['1991到1995年', 0],
        ['1996到2000年', 0],
        ['2001到2005年', 0],
        ['2006到2010年', 0],
        ['2011到2015年', 0],
        ['2016年至今', 0],
    ]
    colors = []
    while True:
        color = random.choice(
            [
                "#c23531",
                "#2f4554",
                "#61a0a8",
                "#d48265",
                "#749f83",
                "#ca8622",
                "#bda29a",
                "#6e7074",
                "#546570",
                "#c4ccd3",
                "#f05b72",
                "#444693",
                "#726930",
                "#b2d235",
                "#6d8346",
                "#ac6767",
                "#1d953f",
                "#6950a1",
            ]
        )
        if color not in colors:
            colors.append(color)
        if len(colors) == len(data):
            break
    conn = pymysql.connect(host='120.79.165.140',
                           user='kino',
                           passwd="student",
                           db='python_web_spider_DB')
    cur = conn.cursor()

    sql1 = "SELECT 上映年份 from wh_doubanmovie"

    cur.execute(sql1)
    for i in cur:
        year = int(str(i).split('\'')[1])
        if year <= 1990:
            data[0][1] += 1
        elif 1990 < year <= 1995:
            data[1][1] += 1
        elif 1995 < year <= 2000:
            data[2][1] += 1
        elif 2000 < year <= 2005:
            data[3][1] += 1
        elif 2005 < year <= 2010:
            data[4][1] += 1
        elif 2010 < year <= 2015:
            data[5][1] += 1
        elif 2015 < year:
            data[6][1] += 1

    c = (
        Pie()
        .add("", data)
        .set_colors(colors)
        # .add("", [list(z) for z in zip(Faker.choose(), Faker.values())])
        # .set_colors(["blue", "green", "yellow", "red", "pink", "orange", "purple"])
        .set_global_opts(title_opts=opts.TitleOpts(title=""))
        .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}"))
    )
    cur.close()
    conn.close()
    return HttpResponse(c.render_embed('豆瓣电影排行top250年份分布.html'))


def word_cloud(request):
    x = []
    data = []
    delete = ['的','你','我','他','说','了','话','这','是','吗','吧','都',
    '也','吗','吧','都','不','为','他们','啊','则','和','在',]
    conn = pymysql.connect(host='120.79.165.140',
                           user='kino',
                           passwd="student",
                           db='python_web_spider_DB')
    cur = conn.cursor()

    sql1 = "SELECT comments from xjh_wangyiyun"

    cur.execute(sql1)
    txt = ''
    for i in cur:
        ss = str(i)
        if '\'' in ss:
            txt += ss.split('\'')[1]
    ls = jieba.lcut(txt)
    for item in ls:
        if re.match(r'^([\u4e00-\u9fa5]+)$', item):
            x.append(item)
    for item in x[::]:
        t = (item, x.count(item)*3)
        data.append(t)
        while item in x:
            x.remove(item)
    for item in data:
        if item[1] == 0 or item[0] in delete:
            data.remove(item)
    data.sort(key=lambda x: x in data)

    c = (
        WordCloud()
            .add(series_name="歌曲:Mood 的评论高频词", data_pair=data, word_size_range=[10, 70])
            .set_global_opts(
            title_opts=opts.TitleOpts(
                title="网易云歌曲评论词云", title_textstyle_opts=opts.TextStyleOpts(font_size=23)
            ),
            tooltip_opts=opts.TooltipOpts(is_show=True),
        )
    )

    cur.close()
    conn.close()

    return HttpResponse(c.render_embed('网易云歌曲评论词云.html'))

# 从这里写你们的爬虫函数,例：
# def spider_fun(url, web_name):
#     pass