第二次作业

作业①

1)WeatherForecast

要求:在中国气象网http://www.weather.com.cn给定城市集的7日天气预报，并保存在数据库。
代码:

from bs4 import BeautifulSoup
from bs4 import UnicodeDammit
import urllib.request
import sqlite3


class WeatherDB:  # 包含对数据库的操作
    def openDB(self):
        self.con = sqlite3.connect('weathers.db')
        self.cursor = self.con.cursor()
        try:
            self.cursor.execute(
                'create table weathers (wCity varchar(16),wDate varchar(16),wWeather varchar(64),wTemp varchar(32),constraint pk_weather primary key(wCity,wDate))')
        except:  # 第一次创建表格是成功的；第二次创建就会清空表格
            self.cursor.execute('delete from weathers')

    def closeDB(self):
        self.con.commit()
        self.con.close()

    def insert(self, city, date, weather, temp):
        try:
            self.cursor.execute('insert into weathers (wCity,wDate,wWeather,wTemp)values(?,?,?,?)',
                                (city, date, weather, temp))                ## 爬取城市的天气预报数据储存到数据库weather.db中
        except Exception as err:
            print(err)

    def show(self):
        self.cursor.execute('select * from weathers')   #执行查询语句，输出表
        rows = self.cursor.fetchall()
        print('%-16s%-16s%-32s%-16s' % ('city', 'date', 'weather', 'temp'))
        for row in rows:
            print('%-16s%-16s%-32s%-16s' % (row[0], row[1], row[2], row[3]))   


class WeatherForecast:  
    def __init__(self):
        self.headers = {
            'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.0 x64; en-US;rv:1.9pre)Gecko/2019100821 Minefield/3.0.2pre'}  # 创建头，伪装成服务器/浏览器访问远程的web服务器
        self.cityCode = {'北京': '101010100', '上海': '101020100', '广州': '101280101', '深圳': '101280601'}  # 查找的城市

    def forecastCity(self, city):
        if city not in self.cityCode.keys():
            print(city + 'code cannot be found')
            return

        url = 'http://www.weather.com.cn/weather/' + self.cityCode[city] + '.shtml' 
        try:
            req = urllib.request.Request(url, headers=self.headers)  
            data = urllib.request.urlopen(req)
            data = data.read()
            dammit = UnicodeDammit(data, ['utf-8'], 'gbk')
            data = dammit.unicode_markup
            soup = BeautifulSoup(data, 'lxml')
            lis = soup.select("ul[class='t clearfix'] li")  # 找到每一个天气数据
            for li in lis:
                try:
                    date = li.select('h1')[0].text
                    weather = li.select('p[class="wea"]')[0].text
                    temp = li.select('p[class="tem"] span')[0].text + '/' + li.select('p[class="tem"] i')[0].text
                    print(city, date, weather, temp)
                    self.db.insert(city, date, weather, temp)  # 插入到数据库的记录
                except Exception as err:
                    print(err)
        except Exception as err:
            print(err)

    def process(self, cities):
        self.db = WeatherDB()
        self.db.openDB()
        for city in cities:
            self.forecastCity(city)  # 循环每一个城市
        self.db.show()
        self.db.closeDB()

ws = WeatherForecast()
ws.process(['北京', '上海', '广州', '深圳'])
print('completed')

运行结果部分截图

2)心得体会:

这次的代码就是按照书上敲的，遇到不懂的也通过度娘解决了，这次主要是加强了Beautiful的使用以及对sqlite数据库有初步了解。

作业②

2)

要求:用requests和BeautifulSoup库方法定向爬取股票相关信息。
候选网站：东方财富网https://www.eastmoney.com/

​新浪股票http://finance.sina.com.cn/stock/

技巧：在谷歌浏览器中进入F12调试模式进行抓包，查找股票列表加载使用的url，并分析api返回的值，并根据所要求的参数可适当更改api的请求参数。根据URL可观察请求的参数f1、f2可获取不同的数值，根据情况可删减请求的参数。
思路:
通过数据的url对比，可以发现同一板块的数据页数对应的是pn参数

而同一页数不同板块的数据对应的是fid和fs参数

参考链接：https://zhuanlan.zhihu.com/p/50099084
代码:

import requests
import re
import math

# 用get方法访问服务器并提取页面数据
def getHtml(cmd, page):
    url = "http://68.push2.eastmoney.com/api/qt/clist/get?cb=jQuery112409784442493077996_1601810442107&pn=" + str(
        page) + "&pz=20&po=1&np=1&ut=bd1d9ddb04089700cf9c27f6f7426281&fltt=2&invt=2&" + cmd + "&fields=f1,f2,f3,f4,f5,f6,f7,f8,f9,f10,f12,f13,f14,f15,f16,f17,f18,f20,f21,f23,f24,f25,f22,f11,f62,f128,f136,f115,f152"
    r = requests.get(url)
    pat = ""diff":[(.*?)]"
    data = re.compile(pat, re.S).findall(r.text)[0]
    all_page = math.ceil(eval(re.findall('"total":(d+)', r.text)[0]) / 20)    #获取板块的数据条数，除20向上取整就是页数
    return data, all_page

# 获取单个页面股票数据
def getOnePageStock(cmd, page):
    data, all_page = getHtml(cmd, page)
    datas = data.split("},")          #分解每条股票
    global p
    for i in range(len(datas)):
        p += 1
        stocks = re.sub('["{}]', '', datas[i]).split(",")     #分解股票的每条属性
        print(tplt.format(p, stocks[11].split(":")[1], stocks[13].split(":")[1], stocks[1].split(":")[1],      #输出股票内容
                          stocks[2].split(":")[1], stocks[3].split(":")[1],
                          stocks[4].split(":")[1], stocks[5].split(":")[1], stocks[6].split(":")[1],
                          stocks[14].split(":")[1], stocks[15].split(":")[1],
                          stocks[16].split(":")[1], stocks[17].split(":")[1], chr(12288)))


cmd = {
    "沪深A股": "fid=f3&fs=m:0+t:6,m:0+t:13,m:0+t:80,m:1+t:2,m:1+t:23",            
    "上证A股": "fid=f3&fs=m:1+t:2,m:1+t:23",
    "深证A股": "fid=f3&fs=m:0+t:6,m:0+t:13,m:0+t:80",
    "新股": "fid=f26&fs=m:0+f:8,m:1+f:8",
    "中小板": "fid=f3&fs=m:0+t:13",
    "创业板": "fid=f3&fs=m:0+t:80"
}
for i in cmd.keys():
    tplt = "{0:^13}{1:^13}{2:{13}^13}{3:^13}{4:^13}{5:^13}{6:^13}{7:^13}{8:^13}{9:^13}{10:^13}{11:^13}{12:^13}"
    print(i)
    print("{0:^11}{1:^11}{2:{13}^12}{3:^12}{4:^12}{5:^12}{6:^10}{7:^10}{8:^12}{9:^12}{10:^12}{11:^12}{12:^12}".format(
        "序号", "股票代码", "股票名称", "最新报价", "涨跌幅", "涨跌额", "成交量", "成交额", "振幅", "最高", "最低", "今开", "昨收", chr(12288)))
    page = 1
    p = 0
    stocks, all_page = getHtml(cmd[i], page)
    while True:
        page += 1
        if page <= all_page:                #页数判断
            getOnePageStock(cmd[i], page)
        else:
            break

运行结果部分截图:

2)心得体会:

这次实验的是抓取js动态加载的网页，在获取数据方面花费的很长时间，再有就是板块的页数（最后还是借鉴同学的），还是有很大收获的。

作业③

3)

要求:根据自选3位数+学号后3位选取股票，获取印股票信息。抓包方法同作②。
候选网站：东方财富网https://www.eastmoney.com/

​新浪股票http://finance.sina.com.cn/stock/
代码:

import requests
import re
import math


# 用get方法访问服务器并提取页面数据
def getHtml(cmd, page):
    url = "http://68.push2.eastmoney.com/api/qt/clist/get?cb=jQuery112409784442493077996_1601810442107&pn=" + str(
        page) + "&pz=20&po=1&np=1&ut=bd1d9ddb04089700cf9c27f6f7426281&fltt=2&invt=2&" + cmd + "&fields=f1,f2,f3,f4,f5,f6,f7,f8,f9,f10,f12,f13,f14,f15,f16,f17,f18,f20,f21,f23,f24,f25,f22,f11,f62,f128,f136,f115,f152"
    r = requests.get(url)
    pat = ""diff":[(.*?)]"
    data = re.compile(pat, re.S).findall(r.text)[0]
    all_page = math.ceil(eval(re.findall('"total":(d+)', r.text)[0]) / 20)
    return data, all_page


# 获取单个页面股票数据
def getOnePageStock(cmd, page):
    data, all_page = getHtml(cmd, page)
    datas = data.split("},")
    for i in range(len(datas)):
        stocks = re.sub('["{}]', '', datas[i]).split(",")
        if (stocks[11].split(":")[1] == "002105"):
            print(tplt.format("股票代码号", "股票名称", "今日开", "今日最高", "今日最低", chr(12288)))
            print(tplt.format(stocks[11].split(":")[1], stocks[13].split(":")[1], stocks[16].split(":")[1],
                              stocks[14].split(":")[1],
                              stocks[15].split(":")[1], chr(12288)))
            global p               #找到就输出，并置p=1，跳出循环
            p = 1
            break


cmd = {
    "沪深A股": "fid=f3&fs=m:0+t:6,m:0+t:13,m:0+t:80,m:1+t:2,m:1+t:23",
    "上证A股": "fid=f3&fs=m:1+t:2,m:1+t:23",
    "深证A股": "fid=f3&fs=m:0+t:6,m:0+t:13,m:0+t:80",
    "新股": "fid=f26&fs=m:0+f:8,m:1+f:8",
    "中小板": "fid=f3&fs=m:0+t:13",
    "创业板": "fid=f3&fs=m:0+t:80"
}
p = 0
for i in cmd.keys():
    tplt = "{0:^8}	{1:{5}^8}	{2:^8}	{3:^8}	{4:^8}"
    page = 1
    stocks, all_page = getHtml(cmd[i], page)
    # 自动爬取多页，并在结束时停止
    while True:
        page += 1
        if page <= all_page:
            getOnePageStock(cmd[i], page)
        else:
            break
        if p == 1:
            break
if p == 0:
    print("没找到对应的股票代码")

运行结果：

2)心得体会:

我好像是只是在第二题的基础上加了一个if判断，感觉没有理解题目的意思。。。