Shuiwu/n05_sc.py

#!/usr/bin/env python
# coding:utf-8

import requests,json,re
from rety import retry
from setting import proxies
from urllib import parse
from lxml import etree
from mongo_cho import myco5
r = requests.session()
r.keep_alive = False
import urllib3
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)

@retry(3)
def r1_d(url,dt):
    # url = 'https://sichuan.chinatax.gov.cn/art/2021/3/23/art_15873_10537.html'
    headers = {
        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.85 Safari/537.36",
    }
    response = r.get(url=url,headers=headers,verify=False,proxies=proxies)
    response.encoding = 'UTF-8'
    html= response.text
    # print(html)
    selector = etree.HTML(html)
    a = selector.xpath('//tbody//tr')
    dict1 = {}
    try:
        for i in a:
            k1 = i.xpath('td[1]')
            text = k1[0].xpath('string(.)').strip()
            # print(text)
            v1 = i.xpath('td[2]')
            text1 = v1[0].xpath('string(.)').strip()
            v2 = text1.replace(' ','').replace('\r','').replace('\t','').replace('\n','')
            dict1[text] = v2
    except:
        pass
    print(dict1)
    dict1['url'] = url
    dict1['date'] = dt
    return dict1

# r1_d()
@retry(3)
def r1(icid,cpg,dt):
    url = 'https://sichuan.chinatax.gov.cn/module/search/index.jsp'
    headers = {
        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.85 Safari/537.36",
    }
    params = {
        "vc_name":"",
        "field_439": "",
        "field_440": "",
        "field_441": "",
        "field_442": "",
        "field_443": "",
        "strSelectID": "390,439,440,441,442,443",
        "i_columnid": icid,
        "field": "vc_name:1:0,field_439:1:0,field_440:1:0,field_441:1:0,field_442:1:0,field_443:1:0",
        "currpage": cpg,
    }
    response = r.get(url=url,headers=headers,params=params,verify=False,proxies=proxies)
    html = response.text
    # print(html)
    selector = etree.HTML(html)
    a = selector.xpath('//tr/td[5]/a/@href')
    list1 = []
    for i in a:
        # print(i)
        url1 = i.replace('../..','https://sichuan.chinatax.gov.cn')
        print(url1)
        rsd = r1_d(url1,dt)
        list1.append(rsd)
    # print(list1)
    myco5.insert_many(list1)
        # 'https://sichuan.chinatax.gov.cn'


# https://sichuan.chinatax.gov.cn/col/col15873/index.html
##季度更新，对比上次页数，
def runs():
    icid='15873'  #季度id
    tpg=9         #总共几页
    dt='2023/10'   #时限
    for i in range(1,tpg+1):
        print(i,'==================')
        r1(icid,i,dt)
runs()