百度飞桨7天入门课体验
偶然的机会从公众号中发现了百度飞桨从小白逆袭到大神的课程,课程结束,物超所值。
7天的课程全程免费,课程内容丰富,作业环环相扣,还有在线微信群大神全程指导!
第一天:python基础学习
作业文件的查找与存储
内容:熟悉python中os的使用
#导入OS模块
import os
#待搜索的目录路径
path = "Day1-homework"
#待搜索的名称
filename = "2020"
#定义保存结果的数组
result = []
index = 0
def findfiles(path):
'''for root, dirs, files in os.walk(path):
for filename in files:
print(os.path.join(root, filename))'''
global index
files = os.listdir(path)
for file in files:
file_path = os.path.join(path,file)
if os.path.isdir(file_path):
findfiles(file_path)
else:
if filename in file_path:
index =index + 1
result.append(index)
result.append(file_path)
print(result)
result.clear()
if __name__ == '__main__':
findfiles(path)
第二天内容:
主要内容:网络爬虫,requests库与beautifulSoup4库的使用
爬虫内容
1.发送请求(requests模块)
2.获取响应数据(服务器返回)
3.解析并提取数据(BeautifulSoup查找或者re正则)
4.保存数据
一、爬取百度百科中《青春有你2》中所有参赛选手信息,返回页面数据
import json
import re
import requests
import datetime
from bs4 import BeautifulSoup
import os
#获取当天的日期,并进行格式化,用于后面文件命名,格式:20200420today = datetime.date.today().strftime('%Y%m%d')
def crawl_wiki_data(): """ 爬取百度百科中《青春有你2》中参赛选手信息,返回html """
headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36' }
url='https://baike.baidu.com/item/青春有你第二季'
try:
response = requests.get(url,headers=headers)
print(response.status_code)
#将一段文档传入BeautifulSoup的构造方法,就能得到一个文档的对象, 可以传入一段字符串
soup = BeautifulSoup(response.text,'lxml') #返回的是class为table-view log-set-param的<table>所有标签 tables = soup.find_all('table',{'class':'table-view log-set-param'})
crawl_table_title = "参赛学员"
for table in tables:
#对当前节点前面的标签和字符串进行查找
table_titles=able.find_previous('div').find_all('h3')
for title in table_titles:
if(crawl_table_title in title):
return table
except Exception as e:
print(e)
二、对爬取的页面数据进行解析,并保存为JSON文件
def parse_wiki_data(table_html):
''' 从百度百科返回的html中解析得到选手信息,以当前日期作为文件名,存JSON文件,保存到work目录下 '''
bs = BeautifulSoup(str(table_html),'lxml')
all_trs = bs.find_all('tr')
error_list = ['\'','\"']
stars = []
for tr in all_trs[1:]:
all_tds = tr.find_all('td')
star = {}
#姓名
star["name"]=all_tds[0].text
#个人百度百科链接
star["link"]= 'https://baike.baidu.com' + all_tds[0].find('a').get('href')
#籍贯
star["zone"]=all_tds[1].text
#星座
star["constellation"]=all_tds[2].text
#身高
star["height"]=all_tds[3].text
#体重
star["weight"]= all_tds[4].text
#花语,去除掉花语中的单引号或双引号
flower_word = all_tds[5].text
for c in flower_word:
if c in error_list:
flower_word=flower_word.replace(c,'')
star["flower_word"]=flower_word
#公司
if not all_tds[6].find('a') is None:
star["company"]= all_tds[6].find('a').text
else:
star["company"]= all_tds[6].text
stars.append(star)
json_data = json.loads(str(stars).replace("\'","\""))
with open('work/' + today + '.json', 'w', encoding='UTF-8') as f:
json.dump(json_data, f, ensure_ascii=False)
三、爬取每个选手的百度百科图片,并进行保存
def crawl_pic_urls():
''' 爬取每个选手的百度百科图片,并保存 '''
with open('work/'+ today + '.json', 'r', encoding='UTF-8') as file:
json_array = json.loads(file.read())
headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36' }
for star in json_array:
name = star['name']
link = star['link']
#!!!请在以下完成对每个选手图片的爬取,将所有图片url存储在一个列表pic_urls中!!!
response = requests.get(link,headers=headers)
bs = BeautifulSoup(response.text,'lxml')
pic_list_url = bs.select('.summary-pic a')[0].get('href')
pic_list_url = 'https://baike.baidu.com' + pic_list_url #获取图片存储页面
pic_list_response = requests.get(pic_list_url,headers=headers)
bs = BeautifulSoup(pic_list_response.text,'lxml')
pic_list_html = bs.select('.pic-list img ')
pic_urls=[]
for pic_html in pic_list_html:
pic_url = pic_html.get('src')
pic_urls.append(pic_url)
down_pic(name,pic_urls)
def down_pic(name,pic_urls):
''' 根据图片链接列表pic_urls, 下载所有图片,保存在以name命名的文件夹中, '''
path = 'work/'+'pics/'+name+'/'
if not os.path.exists(path):
os.makedirs(path)
for i, pic_url in enumerate(pic_urls):
try:
pic = requests.get(pic_url, timeout=15)
string = str(i + 1) + '.jpg'
with open(path+string, 'wb') as f:
f.write(pic.content)
print('成功下载第%s张图片: %s' % (str(i + 1), str(pic_url)))
except Exception as e:
print('下载第%s张图片时失败: %s' % (str(i + 1), str(pic_url)))
print(e)
continue
四、打印爬取的所有图片的路径
def show_pic_path(path):
''' 遍历所爬取的每张图片,并打印所有图片的绝对路径 '''
pic_num = 0
for (dirpath,dirnames,filenames) in os.walk(path):
for filename in filenames:
pic_num += 1
print("第%d张照片:%s" % (pic_num,os.path.join(dirpath,filename)))
print("共爬取《青春有你2》选手的%d照片" % pic_num)
if __name__ == '__main__':
#爬取百度百科中《青春有你2》中参赛选手信息,返回html
html = crawl_wiki_data()
#解析html,得到选手信息,保存为json文件
parse_wiki_data(html)
#从每个选手的百度百科页面上爬取图片,并保存
crawl_pic_urls()
#打印所爬取的选手图片路径
show_pic_path('/home/aistudio/work/pics/')
print("所有信息爬取完成!")
第三天 选手数据分析
本节课重点是numpy 、matplotlib、PIL、pandas等库的使用
选手区域分布图
import matplotlib.pyplot as plt
import numpy as np
import jsonimport matplotlib.font_manager as font_manager
#显示matplotlib生成的图形%matplotlib inline
with open('data/data31557/20200422.json', 'r', encoding='UTF-8') as file:
json_array = json.loads(file.read())
#绘制小姐姐区域分布柱状图,x轴为地区,y轴为该区域的小姐姐数量
zones = []
for star in json_array:
zone = star['zone']
zones.append(zone)
print(len(zones))
print(zones)
'''zone_list = []
count_list = []
for zone in zones:
if zone not in zone_list:
count = zones.count(zone)
zone_list.append(zone)
count_list.append(count)'''
count_dic={}
for zone in zones:
count_dic[zone]=count_dic.get(zone,0)+1
zone_list=list(count_dic.keys())
count_list=list(count_dic.values())
print(zone_list)
print(count_list)# 设置显示中文plt.rcParams['font.sans-serif'] = ['SimHei'] # 指定默认字体
plt.figure(figsize=(20,15))
plt.bar(range(len(count_list)), count_list,color='r',tick_label=zone_list,facecolor='#9999ff',edgecolor='white')
# 这里是调节横坐标的倾斜度,rotation是度数,以及设置刻度字体大小
plt.xticks(rotation=45,fontsize=20)
plt.yticks(fontsize=20)
plt.legend()
plt.title('''《青春有你2》参赛选手''',fontsize = 24)
plt.savefig('/home/aistudio/work/result/bar_result.jpg')plt.show()
选手体重饼图
import matplotlib.pyplot as plt
import numpy as np
import json
import matplotlib.font_manager as font_manager
import pandas as pd
#显示matplotlib生成的图形
%matplotlib inline
df = pd.read_json(r'data/data31557/20200422.json')
weights = df['weight']
arrs = weights.values
for i in range(len(arrs)):
arrs[i]=float(arrs[i][0:-2])#将kg去掉bin = [0,45,50,55,100]#将数据按照bin进行切割
se1 = pd.cut(arrs,bin)
sizes = pd.value_counts(se1)#进行计数,并排序
labels = '<=45kg','45kg~50kg','50kg~55kg','>55kg'explode = (0.1,0.1,0.1,0)
#fig1,ax1 = plt.subplots()
ax1=plt.subplot(111)
ax1.pie(sizes,explode=explode,labels=labels,autopct='%1.1f%%',shadow = True,startangle=165)
ax1.axis('equal')
plt.savefig('/home/aistudio/work/result/pie_result01.jpg')
plt.show()
'''