前言
本文的文字及图片来源于网络,仅供学习、交流使用,不具有任何商业用途,如有问题请及时联系我们以作处理。
PS：如有需要Python学习资料的小伙伴可以加点击下方链接自行获取
python免费学习资料以及群交流解答点击即可加入
-
利用lxml中的xpath提取信息
xpath是一门在 xml文档中查找信息的语言，xpath可用来在 xml 文档中对元素和属性进行遍历。对比正则表达式 re两者可以完成同样的工作，实现的功能也差不多，但xpath明显比re具有优势。具有如下优点：(1)可在xml中查找信息 ；(2)支持html的查找；(3)通过元素和属性进行导航
-
利用xlsxwriter模块将信息保存只excel
xlsxwriter是操作excel的库，可以帮助我们高效快速的，大批量的，自动化的操作excel。它可以写数据，画图，完成大部分常用的excel操作。缺点是xlsxwriter 只能创建新文件，不可以修改原有文件，如果创建新文件时与原有文件同名，则会覆盖原有文件。
-
爬取思路
观察发现贝壳网租房信息总共是100页，我们可以分每页获取到html代码，然后提取需要的信息保存至字典，将所有页面的信息汇总，最后将字典数据写入excel。
-
爬虫源代码
import requests
import time
from lxml import etree
import xlsxwriter
'''
遇到不懂的问题？Python学习交流群：1136201545满足你的需求，资料都已经上传群文件，可以自行下载！
'''
def get_html(page):
"""获取网站html代码"""
url = "https://bj.zu.ke.com/zufang/pg{}/#contentList".format(page)
headers = {
'user-agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36'
}
response = requests.get(url, headers=headers).text
return response
def parse_html(htmlcode, data):
"""解析html代码"""
content = etree.HTML(htmlcode)
results = content.xpath('///div[@class="content__article"]/div[1]/div')
for result in results[:]:
community = result.xpath('./div[1]/p[@class="content__list--item--title twoline"]/a/text()')[0].replace('\n',
'').strip().split()[
0]
address = "-".join(result.xpath('./div/p[@class="content__list--item--des"]/a/text()'))
landlord = result.xpath('./div/p[@class="content__list--item--brand oneline"]/text()')[0].replace('\n',
'').strip() if len(
result.xpath('./div/p[@class="content__list--item--brand oneline"]/text()')) > 0 else ""
postime = result.xpath('./div/p[@class="content__list--item--time oneline"]/text()')[0]
introduction = ",".join(result.xpath('./div/p[@class="content__list--item--bottom oneline"]/i/text()'))
price = result.xpath('./div/span/em/text()')[0]
description = "".join(result.xpath('./div/p[2]/text()')).replace('\n', '').replace('-', '').strip().split()
area = description[0]
count = len(description)
if count == 6:
orientation = description[1] + description[2] + description[3] + description[4]
elif count == 5:
orientation = description[1] + description[2] + description[3]
elif count == 4:
orientation = description[1] + description[2]
elif count == 3:
orientation = description[1]
else:
orientation = ""
pattern = description[-1]
floor = "".join(result.xpath('./div/p[2]/span/text()')[1].replace('\n', '').strip().split()).strip() if len(
result.xpath('./div/p[2]/span/text()')) > 1 else ""
date_time = time.strftime("%Y-%m-%d", time.localtime())
"""数据存入字典"""
data_dict = {
"community": community,
"address": address,
"landlord": landlord,
"postime": postime,
"introduction": introduction,
"price": '￥' + price,
"area": area,
"orientation": orientation,
"pattern": pattern,
"floor": floor,
"date_time": date_time
}
data.append(data_dict)
def excel_storage(response):
"""将字典数据写入excel"""
workbook = xlsxwriter.Workbook('./beikeHouse.xlsx')
worksheet = workbook.add_worksheet()
"""设置标题加粗"""
bold_format = workbook.add_format({'bold': True})
worksheet.write('A1', '小区名称', bold_format)
worksheet.write('B1', '租房地址', bold_format)
worksheet.write('C1', '房屋来源', bold_format)
worksheet.write('D1', '发布时间', bold_format)
worksheet.write('E1', '租房说明', bold_format)
worksheet.write('F1', '房屋价格', bold_format)
worksheet.write('G1', '房屋面积', bold_format)
worksheet.write('H1', '房屋朝向', bold_format)
worksheet.write('I1', '房屋户型', bold_format)
worksheet.write('J1', '房屋楼层', bold_format)
worksheet.write('K1', '查看日期', bold_format)
row = 1
col = 0
for item in response:
worksheet.write_string(row, col, item['community'])
worksheet.write_string(row, col + 1, item['address'])
worksheet.write_string(row, col + 2, item['landlord'])
worksheet.write_string(row, col + 3, item['postime'])
worksheet.write_string(row, col + 4, item['introduction'])
worksheet.write_string(row, col + 5, item['price'])
worksheet.write_string(row, col + 6, item['area'])
worksheet.write_string(row, col + 7, item['orientation'])
worksheet.write_string(row, col + 8, item['pattern'])
worksheet.write_string(row, col + 9, item['floor'])
worksheet.write_string(row, col + 10, item['date_time'])
row += 1
workbook.close()
def main():
all_datas = []
"""网站总共100页，循环100次"""
for page in range(1, 100):
html = get_html(page)
parse_html(html, all_datas)
excel_storage(all_datas)
if __name__ == '__main__':
main()
5. 信息截图