# 數(shù)據(jù)請求模塊 --> 第三方模塊, 需要安裝 pip install requests
import requests
# 解析數(shù)據(jù)模塊 --> 第三方模塊, 需要安裝 pip install parsel
import parsel
# csv模塊
import csv

f = open('data.csv', mode='w', encoding='utf-8', newline='')
csv_writer = csv.DictWriter(f, fieldnames=[
    '標(biāo)題',
    '小區(qū)',
    '區(qū)域',
    '售價(jià)',
    '單價(jià)',
    '戶型',
    '面積',
    '朝向',
    '裝修',
    '樓層',
    '年份',
    '建筑類型',
    '詳情頁',
])
csv_writer.writeheader()

headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.0.0 Safari/537.36'
}

url = 'https://cs.lianjia.com/ershoufang/'

# 完整源碼，視頻講解直接＋這個(gè)扣裙：279199867 免費(fèi)領(lǐng)取

response = requests.get(url=url, headers=headers)
# <Response [200]> 響應(yīng)對象 200 狀態(tài)碼 表示請求成功
print(response)

selector = parsel.Selector(response.text)

lis = selector.css('.sellListContent li.clear')

for li in lis:
    """

    提取具體房源信息: 標(biāo)題 / 價(jià)格 / 位置 / 戶型...
    .title a --> 表示定位class類名為title下面a標(biāo)簽
    """
    title = li.css('.title a::text').get()  # 標(biāo)題
    info_list = li.css('.positionInfo a::text').getall()
    area = info_list[0]  # 小區(qū)名字
    area_1 = info_list[1]  # 地區(qū)
    totalPrice = li.css('.totalPrice span::text').get()  # 售價(jià)
    unitPrice = li.css('.unitPrice span::text').get().replace('元/平', '').replace(',', '')  # 單價(jià)
    houseInfo = li.css('.houseInfo::text').get().split(' | ')  # 信息
    houseType = houseInfo[0]  # 戶型
    houseArea = houseInfo[1].replace('平米', '')  # 面積
    houseFace = houseInfo[2]  # 朝向
    fitment = houseInfo[3]  # 裝修
    fool = houseInfo[4]  # 樓層

    if len(houseInfo) == 7 and '年' in houseInfo[5]:
        year = houseInfo[5].replace('年建', '')
    else:
        year = ''
    house = houseInfo[-1]  # 建筑類型
    href = li.css('.title a::attr(href)').get()  # 詳情頁
    dit = {
        '標(biāo)題': title,
        '小區(qū)': area,
        '區(qū)域': area_1,
        '售價(jià)': totalPrice,
        '單價(jià)': unitPrice,
        '戶型': houseType,
        '面積': houseArea,
        '朝向': houseFace,
        '裝修': fitment,
        '樓層': fool,
        '年份': year,
        '建筑類型': house,
        '詳情頁': href,
    }
    csv_writer.writerow(dit)
    print(dit)
    # print(title, area, area_1, totalPrice, unitPrice, houseType, houseArea, houseFace, fitment, fool, year, house, href)

import requests
import parsel
import re
import csv
# 線程池模塊
import concurrent.futures
import time

def get_response(html_url):

:param html_url:
:return:
"""
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.0.0 Safari/537.36'
}
response = requests.get(url=html_url, headers=headers)
return response

def get_content(html_url):
    """
    :param html_url:
    :return:
    """
    response = get_response(html_url)
    html_data = get_response(link).text
    selector = parsel.Selector(response.text)
    select = parsel.Selector(html_data)
    lis = selector.css('.sellListContent li')
    content_list = []
    for li in lis:

        title = li.css('.title a::text').get()  # 標(biāo)題
        area = '-'.join(li.css('.positionInfo a::text').getall())  # 小區(qū)
        Price = li.css('.totalPrice span::text').get()  # 總價(jià)
        Price_1 = li.css('.unitPrice span::text').get().replace('元/平', '')  # 單價(jià)
        houseInfo = li.css('.houseInfo::text').get()  # 信息
        HouseType = houseInfo.split(' | ')[0]  # 戶型
        HouseArea = houseInfo.split(' | ')[1].replace('平米', '')  # 面積
        direction = houseInfo.split(' | ')[2].replace(' ', '')  # 朝向
        renovation = houseInfo.split(' | ')[3]  # 裝修
        floor_info = houseInfo.split(' | ')[4]
        floor = floor_info[:3]  # 樓層
        floor_num = re.findall('(\d+)層', floor_info)[0]  # 層數(shù)
        BuildingType = houseInfo.split(' | ')[-1]
        string = select.css('.comments div:nth-child(7) .comment_text::text').get()
        href = li.css('.title a::attr(href)').get()  # 詳情頁
        if len(houseInfo.split(' | ')) == 6:
            date = 'None'
        else:
            date = houseInfo.split(' | ')[5].replace('年建', '')  # 日期
        print(string)
        dit = {
            '標(biāo)題': title,
            '內(nèi)容': string,
            '小區(qū)': area,
            '總價(jià)': Price,
            '單價(jià)': Price_1,
            '戶型': HouseType,
            '面積': HouseArea,
            '朝向': direction,
            '裝修': renovation,
            '樓層': floor,
            '層數(shù)': floor_num,
            '建筑日期': date,
            '建筑類型': BuildingType,
            '詳情頁': href,
        }
        content_list.append(dit)
    return content_list

def main(page):
    """
    :param page:
    :return:
    """
    print(f'===============正在采集第{page}頁的數(shù)據(jù)內(nèi)容===============')
    url = f'https:///ershoufang/yuelu/p{page}/'
    content_list = get_content(html_url=url)
    for content in content_list:
        csv_writer.writerow(content)


if __name__ == '__main__':
    time_1 = time.time()
    link = 'http://******/article/149'
    # 創(chuàng)建文件
    f = open('data多線程.csv', mode='a', encoding='utf-8', newline='')
    csv_writer = csv.DictWriter(f, fieldnames=[
        '標(biāo)題',
        '內(nèi)容',
        '小區(qū)',
        '總價(jià)',
        '單價(jià)',
        '戶型',
        '面積',
        '朝向',
        '裝修',
        '樓層',
        '層數(shù)',
        '建筑日期',
        '建筑類型',
        '詳情頁',
    ])
    csv_writer.writeheader()

    # 線程池執(zhí)行器 max_workers 最大線程數(shù)
    exe = concurrent.futures.ThreadPoolExecutor(max_workers=10)
    for page in range(1, 11):
        exe.submit(main, page)
    exe.shutdown()
    time_2 = time.time()
    use_time = int(time_2 - time_1)
    # 總計(jì)耗時(shí): 9
    print('總計(jì)耗時(shí):', use_time)