祁连网站建设公司中国的网络营销公司
人生苦短，我用python
真的好想出去玩啊！！！
春游啊这是！！！
万物复苏的好季节！！！
python 安装包+资料:点击此处跳转文末名片获取
一、模块使用：
爬虫部分:
-
requests
-
parsel
-
csv
数据分析部分:
-
pandas
-
pyecharts
二、开发环境：
-
python 3.6
-
pycharm
三、流程思路:
1. 确定目标需求
python采集旅游景点数据 / 去哪儿~
2. 发送请求
3. 获取数据
4. 解析数据
5. 保存数据
四、代码展示
采集数据
导入模块
import requests
import parsel
import csv
import time
写入表格
f = open('张家界景点.csv', mode='a', encoding='utf-8-sig', newline='')
csv_writer = csv.DictWriter(f, fieldnames=['景区', '星级', '地区', '热度', '销量', '地址','价格', '简介', '详情页'])
csv_writer.writeheader()
多页采集
for page in range(1, 12):print(f'===============================正在爬取第{page}页数据内容=======================================')time.sleep(2)
请求链接
url = f'https://*****.com/ticket/list_%E5%BC%A0%E5%AE%B6%E7%95%8C.html?from=mps_search_suggest_h&keyword=%E5%BC%A0%E5%AE%B6%E7%95%8C&page={page}'
请求头:把python代码伪装成浏览器 给服务器发送请求
headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.128 Safari/537.36'}response = requests.get(url=url, headers=headers)
获取网页文本数据 response.text
# print(response.text)
解析数据
-
css选择器 根据标签提取数据内容
-
第一次提取 所以景区标签内容 返回的页是一个对象 列表
-
id选择器 直接可以使用# 开头
selector = parsel.Selector(response.text)lis = selector.css('#search-list .sight_item_detail')for li in lis:title = li.css('.name::text').get()level = li.css('.level::text').get() area = li.css('.area a::text').get() hot = li.css('.product_star_level em::attr(title)').get().replace('热度: ', '')hot = int(float(hot)*100)address = li.css('.address span::attr(title)').get() price = li.css('.sight_item_price em::text').get() hot_num = li.css('.hot_num::text').get() intro = li.css('.intro::text').get() href = li.css('.name::attr(href)').get()href = 'https://*****.com/' + hrefdit = {'景区': title,'星级': level,'地区': area,'热度': hot,'销量': hot_num,'地址': address,'价格': price,'简介': intro,'详情页': href,}csv_writer.writerow(dit)print(title, level, area, hot, address, price, hot_num, intro, href, sep=' | ')
旅游数据可视化
导入景点数据
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline
plt.rcParams['font.sans-serif'] = ['SimHei'] # 设置加载的字体名
plt.rcParams['axes.unicode_minus'] = False # 解决保存图像是负号'-'显示为方块的问题
import jieba
import re
from pyecharts.charts import *
from pyecharts import options as opts
from pyecharts.globals import ThemeType
import stylecloud
from IPython.display import Image df = pd.read_csv(r"c:\python\demo2\爬虫入门教程45 五一去哪儿玩？\去哪儿.csv")
df.head()
删除重复数据
df = df.drop_duplicates()
查看数据信息
df.info()
景点价格价格Top20
df_qunarPrice = df.pivot_table(index='景区',values='价格')
df_qunarPrice.sort_values('价格',inplace=True,ascending=False)
df_data = df_qunarPrice[:20]
from pyecharts import options as opts
from pyecharts.charts import Barc = (Bar().add_xaxis(df_data.index.tolist()).add_yaxis("",df_data['价格'].values.tolist()).set_series_opts(label_opts=opts.LabelOpts(is_show=False)).set_global_opts(title_opts=opts.TitleOpts(title="景点价格Top20"),xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=90)),))
c.render_notebook()
评分TOP20景点
df_score = df.pivot_table(index='景区',values='热度')
df_score.sort_values('热度',inplace=True,ascending=False)
df_data = df_score[:20]
from pyecharts import options as opts
from pyecharts.charts import Barc = (Bar().add_xaxis(df_data.index.tolist()).add_yaxis("",df_data['热度'].values.tolist()).set_series_opts(label_opts=opts.LabelOpts(is_show=False)).set_global_opts(title_opts=opts.TitleOpts(title="评分TOP20景点"),xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=90)),))
c.render_notebook()
df_saleCount = df.pivot_table(index='景区',values='销量')
df_saleCount.sort_values('销量',inplace=True,ascending=False)
df_data = df_saleCount[:20]
df_data.values
月销量TOP20景点
df_saleCount = df.pivot_table(index='景区',values='销量')
df_saleCount.sort_values('销量',inplace=True,ascending=False)
df_data = df_saleCount[:20]from pyecharts import options as opts
from pyecharts.charts import Barc = (Bar().add_xaxis(df_data.index.tolist()).add_yaxis("",df_data['销量'].values.tolist()).set_series_opts(label_opts=opts.LabelOpts(is_show=False)).set_global_opts(title_opts=opts.TitleOpts(title="月销量TOP20景点"),xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=90)),))
c.render_notebook()
景点等级分布
df_star = df["星级"].value_counts()
df_star = df_star.sort_values(ascending=False)
print(df_star)
c = (Pie(init_opts=opts.InitOpts(theme=ThemeType.WALDEN)).add("",[list(z) for z in zip(df_star.index.to_list(),df_star.to_list())]).set_global_opts(legend_opts = opts.LegendOpts(is_show = False),title_opts=opts.TitleOpts(title="景点等级分布",subtitle="数据来源：去哪儿网",pos_top="0.5%",pos_left = 'left')).set_series_opts(label_opts=opts.LabelOpts(formatter="{b}:{d}%",font_size=16)))
c.render_notebook()
df[df["星级"]!='无'].sort_values("星级",ascending=False)