CZYC_Pachong/utils/get_message.py

# -*- coding: utf-8 -*-
# @Author  : ChenZhaoyuchen
# @Time    : 2024/9/26 16:20
# @File    : get_message.py

from anjuke.utils.setting import *
from bs4 import BeautifulSoup


def get_province_area():
    Area_list = []
    soup = BeautifulSoup(response_HTML_province, 'html.parser')
    div_table = soup.find(class_='sel-content')

    for area_ in div_table.find_all('a'):
        area = area_.text
        Area_list.append(area)
    # 此处出现错误是因为del操作缩进错误，for循环里append，又del导致输出为空
    del Area_list[0]
    return Area_list


def get_city_area():
    Area_list = []
    soup = BeautifulSoup(response_HTML_province, 'html.parser')
    div_table = soup.find(class_='sel-sec')

    for area_ in div_table.find_all('a'):
        area = area_.text
        Area_list.append(area)
    del Area_list[0]
    return Area_list

def get_qu_area():
    Area_list = []
    soup = BeautifulSoup(response_HTML, 'html.parser')
    div_table = soup.find(class_= 'sel-content')

    for area_ in div_table.find_all('a'):
        area = area_.text
        Area_list.append(area)
    del Area_list[0]
    return Area_list

def get_zhoubian_area():
    Area_list = []
    soup = BeautifulSoup(response_HTML, 'html.parser')
    div_table = soup.find(class_= 'sel-sec')

    for area_ in div_table.find_all('a'):
        area = area_.text
        Area_list.append(area)
    del Area_list[0]
    return Area_list

def get_Year():
    Years_list = []
    soup = BeautifulSoup(response_HTML, 'html.parser')
    years = soup.find(class_="year-list")
    for year_ in years.find_all('a'):
        year = year_.text
        Years_list.append(year)
    return Years_list

def get_area_url():
    Urls_list = []
    soup = BeautifulSoup(response_HTML, 'html.parser')
    urls = soup.find(class_='sel-content')

    for url_area in urls.find_all('a'):
        url_area = url_area.get('href')
        Urls_list.append('https://www.anjuke.com' + url_area)
    del Urls_list[0]
    return Urls_list

def get_zhoubian_url():
    Urls_list = []
    soup = BeautifulSoup(response_HTML, 'html.parser')
    urls = soup.find(class_='sel-sec')

    for url_area in urls.find_all('a'):
        url_area = url_area.get('href')
        Urls_list.append( url_area)
    del Urls_list[0]
    return Urls_list

if __name__ == '__main__':
    # url和response值
    print(urls_template_high,response_200)
    print(urls_template_low,response_2002)
    # 时间跨度及地区唯一url
    print('时间跨度:',get_Year())
    # 分url
    print('省级/直辖市:',get_province_area())
    print('市级:',get_city_area())
    # 分url
    print('区级:',get_qu_area())
    print('区级'+'唯一url:',get_area_url())
    print('周边:',get_zhoubian_area())
    print('周边'+'唯一url:',get_zhoubian_url())
    # # html内容
    # print(response_HTML)