python之scrapy框架

            #
             from scrapy.cmdline import execute
            
#
             # 写终端的命令
            
#
             # scrapy crawl
            
#
             execute(["scrapy","crawl","baidu"])
            from scrapy.cmdline import execute
# execute(["scrapy","genspider","lianjia","lianjia.com"])
# execute("scrapy crawl lianjia".split(" "))
execute("scrapy crawl --nolog lianjia".split(""))

            #
             -*- coding: utf-8 -*-
            import
             scrapy

            from scrapy import Request

# response的类from scrapy.http.response.html import HtmlResponse
class LianjiaSpider(scrapy.Spider):
    name = ‘lianjia‘# 爬虫程序名# 只保留包含lianjia.com的url
    allowed_domains = [‘lianjia.com‘]  # 限制域名# 存放初始请求url
    start_urls = [‘https://bj.lianjia.com/ershoufang/‘]

    def parse(self, response):  # response返回的响应对象# print(response)# print(type(response))# # 获取文本# print(response.text)# print(response.url)# 获取区域列表url
        area_list = response.xpath(‘//div[@data-role="ershoufang"]/div/a‘)

        # 遍历所有区域列表for area in area_list:
            print(area)
            ‘‘‘
            .extract()提取多个
            .extract_first()提取一个
            ‘‘‘# 1、区域名称
            area_name = area.xpath(‘./text()‘).extract_first()
            print(area_name)
            # 2、区域二级url
            area_url = ‘https://bj.lianjia.com/‘ + area.xpath(‘./@href‘).extract_first()
            print(area_url)
            # 会把area_url的请求响应数据交给callback方法# yield后面跟着的都会添加到生成器中yield Request(url=area_url, callback=self.parse_area)


    def parse_area(self, response):
        # print(response)
        house_list = response.xpath(‘//ul[@class="sellListContent"]‘)
        # print(house_list)if house_list:
            for house in house_list:

                house_name = house.xpath(‘.//div[@class="title"]/a/text()‘).extract_first()
                print(house_name)

                house_cost = house.xpath(‘.//div[@class="totalPrice]/text()‘).extract_first() + ‘万‘print(house_cost)

                house_price = house.xpath(‘.//div[@class="unitPrice"]/span/text()‘).extract_first()
                print(house_price)

                pass

            from wxpy import Bot
from pyecharts import Pie
import webbrowser

# 实例化一个微信机器人对象
bot = Bot()

# 获取到微信的所有好友
friends = bot.friends()

# 设定男性\女性\位置性别好友名称
attr = [‘男朋友‘, ‘女朋友‘, ‘人妖‘]

# 初始化对应好友数量
value = [0, 0, 0]

# 遍历所有的好友,判断这个好友是男性还是女性for friend in friends:
    if friend.sex == 1:
        value[0] += 1
    elif friend.sex == 2:
        value[1] += 1
    else:
        value[2] += 1

# 实例化一个饼状图对象
pie = Pie(‘tank的好友们!‘)

# 图表名称str，属性名称list，属性所对应的值list，is_label_show是否现在标签
pie.add(‘‘, attr, value, is_label_show=True)

# 生成一个html文件
pie.render(‘friends.html‘)

# 打开html文件
webbrowser.open(‘friends.html‘)