分析

1. 分析结构，可以发现标题都是h2标签，内容都是p标签，那就直接爬呗！！！

import requests

url = 'http://cpc.people.com.cn/GB/64162/64165/67447/67448/index.html'
response = requests.get(url)
print(response.text)

发现中文乱码

查看编码结果是GB2312，这就好办了，进行解码不就完事了

import requests

url = 'http://cpc.people.com.cn/GB/64162/64165/67447/67448/index.html'
response = requests.get(url)
response.encoding = 'GB2312'
print(response.text)

对比网页源代码发现内容一致，说明人民网没做任何反爬机制，这emmm

2. 获取想要的内容

import requests
from lxml import etree

url = f'http://cpc.people.com.cn/GB/64162/64165/67447/67448/index.html'
response = requests.get(url)
response.encoding = 'GB2312'
# print(response.text)
html = etree.HTML(response.text)

title_pat = '//div[@class="p1_content clearfix"]/div[@class="p1_02 clearfix width884"]/h2/text()'
des_pat = '//div[@class="p1_content clearfix"]/div[@class="p1_02 clearfix width884"]/p/text()'
title = html.xpath(title_pat)
des = html.xpath(des_pat)
# 转换为元组
itemZip = zip(title, des)
# 转换为字典
content = dict(itemZip)
print(content)

3. 我们不知想要当天的，我们还要其他的，分析网址

http://cpc.people.com.cn/GB/64162/64165/67447/67448/index.html
http://cpc.people.com.cn/GB/64162/64165/67447/67449/index.html
http://cpc.people.com.cn/GB/64162/64165/67447/67450/index.html
http://cpc.people.com.cn/GB/64162/64165/67447/67458/index.html
http://cpc.people.com.cn/GB/64162/64165/67447/67506/index.html

发现前面几个还是有规律的，后面就乱序了，这。。，我们从按钮入手

发现查看信息按钮是通过JavaScript脚本go()函数执行的，接下来就是寻找go函数

发现有2个位置有go()函数，点进去可以发现只有cpc_review.js才是我们想要的，找到JavaScript部分就好办了。

发现这不就是switch-case 语句，先通过第一个case分析月份再通过第二个case在定位到月份

显而易见链接前半部分都是相同的，后办部分为月/日，最终确认链接为
http://cpc.people.com.cn/GB/64162/64165/月/日/index.html

这就好办了 那就直接爬呗
但月份正则并不好提取，反正就12个月份，直接手撸呗！！！

上代码hhhh

import re
import requests

monuth = [76621, 77552, 77585, 78561, 79703, 82273, 67447, 68640, 70293, 70486, 72301, 74856]
day_list = []

for item in monuth:
    url = 'http://cpc.people.com.cn/img/2010cpc_lishishangdejintian/cpc_review.js'
    response = requests.get(url).text
    url_pat = f'http://cpc.people.com.cn/GB/64162/64165/{item}/(.*?)/index.html'
    url = re.compile(url_pat).findall(response)
    day_list.append(url)

print(day_list)

项目封装

# 导入包
import re
import requests
import time
from lxml import etree

monuth_list = [76621, 77552, 77585, 78561, 79703, 82273, 67447, 68640, 70293, 70486, 72301, 74856]
day_list = []

def day():
    '''

    :return:
    '''
    for item in monuth_list:
        url = 'http://cpc.people.com.cn/img/2010cpc_lishishangdejintian/cpc_review.js'
        response = requests.get(url).text
        url_pat = f'http://cpc.people.com.cn/GB/64162/64165/{item}/(.*?)/index.html'
        url = re.compile(url_pat).findall(response)
        day_list.append(url)
    # print(day_list)

def search(mon:int, day:int):
    '''
    搜索获取今日党史
    :param mon: 月
    :param day: 日
    :return: 内容
    '''
    mon = monuth_list[mon - 1]
    day = day_list[monuth_list.index(mon)][day - 1]
    url = f'http://cpc.people.com.cn/GB/64162/64165/{mon}/{day}/index.html'
    response = requests.get(url)
    response.encoding = 'GB2312'
    html = etree.HTML(response.text)

    title_pat = '//div[@class="p1_content clearfix"]/div[@class="p1_02 clearfix width884"]/h2/text()'
    des_pat = '//div[@class="p1_content clearfix"]/div[@class="p1_02 clearfix width884"]/p/text()'
    title = html.xpath(title_pat)
    des = html.xpath(des_pat)
    itemZip = zip(title, des)

    # print(dict(itemZip))
    return dict(itemZip)

if __name__ == '__main__':
    day()
    monuth = time.localtime().tm_mon
    day = time.localtime().tm_mday
    print(search(monuth, day))

Flask分装api

# 导入包
import re
import requests
import time
from lxml import etree
from flask import Flask, request, json, Response

monuth_list = [76621, 77552, 77585, 78561, 79703, 82273, 67447, 68640, 70293, 70486, 72301, 74856]
day_list = []


def day():
    '''

    :return:
    '''
    for item in monuth_list:
        url = 'http://cpc.people.com.cn/img/2010cpc_lishishangdejintian/cpc_review.js'
        response = requests.get(url).text
        url_pat = f'http://cpc.people.com.cn/GB/64162/64165/{item}/(.*?)/index.html'
        url = re.compile(url_pat).findall(response)
        day_list.append(url)


def search(mon, day):
    '''
    搜索获取今日党史
    :param mon: 月
    :param day: 日
    :return: 内容
    '''
    mon = monuth_list[int(mon) - 1]
    day = day_list[monuth_list.index(int(mon))][int(day) - 1]
    url = f'http://cpc.people.com.cn/GB/64162/64165/{mon}/{day}/index.html'
    response = requests.get(url)
    response.encoding = 'GB2312'
    html = etree.HTML(response.text)

    title_pat = '//div[@class="p1_content clearfix"]/div[@class="p1_02 clearfix width884"]/h2/text()'
    des_pat = '//div[@class="p1_content clearfix"]/div[@class="p1_02 clearfix width884"]/p/text()'
    title = html.xpath(title_pat)
    des = html.xpath(des_pat)
    itemZip = zip(title, des)

    # print(dict(itemZip))
    return dict(itemZip)


app = Flask(__name__)


@app.route('/')
def index():
    mon = request.args.get("mon")
    day = request.args.get("day")
    if mon == None or day == None:
        mon = time.localtime().tm_mon
        day = time.localtime().tm_mday
    print(mon, day)
    res = {
        'code': 0,
        'tips': '获取成功',
        'data': search(mon, day)
    }
    return Response(json.dumps(res, ensure_ascii=False), mimetype='application/json')


if __name__ == '__main__':
    day()
    app.run()