python-爬蟲-58同城

• 代碼

代碼

from bs4 import BeautifulSoup
import requests
import csv
import time

url = "https://bj.58.com/pinpaigongyu/pn/{page}/?minprice=2000_4000"

#已完成的頁數序号，初時為0
page = 0
# 建立一個有寫權限的csv_file
csv_file = open("rent.csv","w") 
# 建立csv_writer，分隔符','
csv_writer = csv.writer(csv_file, delimiter=',')

while True:

    page += 1
    print("fetch: ", url.format(page=page))
    time.sleep(1)
    # 響應
    response = requests.get(url.format(page=page))
    html = BeautifulSoup(response.text)
    # 在list中選li選項
    house_list = html.select(".list > li")
	
    # 循環在讀不到新的房源時結束
    if not house_list:
        break

    for house in house_list:
        house_title = house.select("h2")[0].string
        house_url = house.select("a")[0]["href"]
        house_info_list = house_title.split()

        # 如果第二列是較高價的電梯大廈名則取第一列作為位址
        if "較高價的電梯大廈" in house_info_list[1] or "青年社群" in house_info_list[1]:
            house_location = house_info_list[0]
        else:
            house_location = house_info_list[1]

        house_money = house.select(".money")[0].select("b")[0].string
        csv_writer.writerow([house_title, house_location, house_money, house_url])

csv_file.close()