爬蟲----大數(shù)據(jù)
XPath語法和lxml模塊
一搂鲫、 提取本地html中的數(shù)據(jù)
- 新建html文件
- 讀取
- 使用xpath語法進(jìn)行提取
- 使用 lxml 中的xpath
- 使用lxml提取 h1標(biāo)簽中的內(nèi)容
.py文件
from lxml import html
# 讀取html文件
with open('./index.html', 'r', encoding='utf-8') as f:
html_data = f.read()
# print(html_data)
# 解析html文件，獲得selector對(duì)象
selector = html.fromstring(html_data)
# selector中調(diào)用xpath方法
# 要獲取標(biāo)簽中的內(nèi)容每币，末尾要添加text()
h1 = selector.xpath('/html/body/h1/text()')
print(h1[0])
# // 可以代表從任意位置出發(fā)创倔、
# //標(biāo)簽1[@屬性=屬性值]/標(biāo)簽2[@屬性=屬性值]..../text()
a = selector.xpath('//div[@id="container"]/a/text()')
print(a)
# 獲取 p標(biāo)簽的內(nèi)容
p = selector.xpath('//div[@id="container"]/p/text()')
print(p)
index.html文件
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>Title</title>
</head>
<body>
<h1>歡迎來到王者榮耀</h1>
<ul>
<li><a ><img src="https://game.gtimg.cn/images/yxzj/img201606/heroimg/508/508.jpg" alt="">伽羅</a></li>
<li><img src="" alt="">孫策/li>
<li>鎧</li>
<li>虞姬</li>
</ul>
<ol>
<li>坦克</li>
<li>戰(zhàn)士</li>
<li>刺客</li>
</ol>
<!--div + css 布局-->
<div>這是div標(biāo)簽</div>
<div id="container">
<p>被動(dòng)：伽羅的普攻與技能傷害將會(huì)優(yōu)先對(duì)目標(biāo)的護(hù)盾效果造成一次等額的傷害</p>
<a >點(diǎn)擊跳轉(zhuǎn)至百度</a>
</div>
<div>這是第二個(gè)div標(biāo)簽</div>
</body>
</html>
運(yùn)行結(jié)果
運(yùn)行結(jié)果
index網(wǎng)頁
二嗡害、 獲取當(dāng)當(dāng)網(wǎng)數(shù)據(jù)
代碼如下：
import requests
from lxml import html
import pandas as pd
from matplotlib import pyplot as plt
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
def spider_dangdang(isbn):
book_list = []
# 目標(biāo)站點(diǎn)地址
url = 'http://search.dangdang.com/?key={}&act=input'.format(isbn)
# print(url)
# 獲取站點(diǎn)str類型的響應(yīng)
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36"}
resp = requests.get(url, headers=headers)
html_data = resp.text
# 將html頁面寫入本地
with open('dangdang.html', 'w', encoding='utf-8') as f:
f.write(html_data)
# 提取目標(biāo)站的信息
selector = html.fromstring(html_data)
ul_list = selector.xpath('//div[@id="search_nature_rg"]/ul/li')
print('您好，共有{}家店鋪售賣此圖書'.format(len(ul_list)))
# 遍歷 ul_list
for li in ul_list:
# 圖書名稱
title = li.xpath('./a/@title')[0].strip()
# print(title)
# 圖書購買鏈接
link = li.xpath('a/@href')[0]
# print(link)
# 圖書價(jià)格
price = li.xpath('./p[@class="price"]/span[@class="search_now_price"]/text()')[0]
#price = float(price.replace('￥',' '))
price = price.replace('￥', '')
# print(price)
# 圖書賣家名稱
store = li.xpath('./p[@class="search_shangjia"]/a/text()')
# if len(store) == 0:
# store = '當(dāng)當(dāng)自營'
# else:
# store = store[0]
store = '當(dāng)當(dāng)自營' if len(store) == 0 else store[0]
# print(store)
# 添加每一個(gè)商家的圖書信息
book_list.append({
'title':title,
'price':price,
'link':link,
'store':store
})
# 按照價(jià)格進(jìn)行排序
book_list.sort(key=lambda x:x['price'])
# 遍歷booklist
for book in book_list:
print(book)
# 展示價(jià)格最低的前10家 柱狀圖
# 店鋪的名稱
top10_store = [book_list[i] for i in range(12)]
# x = []
# for store in top10_store:
# x.append(store['store'])
x = [x['store'] for x in top10_store]
print(x)
# 圖書的價(jià)格
y = [x['price'] for x in top10_store]
print(y)
#plt.bar(x, y)
plt.barh(x, y)
plt.show()
# 存儲(chǔ)成csv文件
df = pd.DataFrame(book_list)
df.to_csv('dangdang.csv')
spider_dangdang('9787115428028')
運(yùn)行結(jié)果：
當(dāng)當(dāng)網(wǎng)TOP10
三三幻、 練習(xí)
提取https://movie.douban.com/cinema/later/chongqing網(wǎng)站以下信息就漾，并且根據(jù)信息完成3，4效果
1.電影名念搬，上映日期抑堡，類型，上映國家朗徊，想看人數(shù)
2.根據(jù)想看人數(shù)進(jìn)行排序
3.繪制即將上映電影國家的占比圖
4.繪制top5最想看的電影
代碼如下：
import requests
from lxml import html
import pandas as pd
from matplotlib import pyplot as plt
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
url='https://movie.douban.com/cinema/later/chongqing/'
resp = requests.get(url)
#獲取站點(diǎn)str類型的
html_data=resp.text
# 提取目標(biāo)站點(diǎn)的信息
selector = html.fromstring(html_data)
movie_info=selector.xpath('//div[@id="showing-soon"]/div')
#print(html_data)
print('你好首妖，共有{}電影即將上映'.format(len(movie_info)))
movie_info_list=[]
for movie in movie_info:
#電影名
movie_name=movie.xpath('./div/h3/a/text()')[0]
# print(movie_name)
#上映日期
movie_date=movie.xpath('./div/ul/li[1]/text()')[0]
# print(movie_date)
#電影類型
movie_type=movie.xpath('./div/ul/li[2]/text()')[0]
movie_type=str(movie_type)
movie_type=movie_type.split(' / ')
# print(type(movie_type))
#print(movie_type)
#上映國家
movie_nation=movie.xpath('./div/ul/li[3]/text()')[0]
# print(movie_nation)
#想看人數(shù)
movie_want = movie.xpath('./div/ul/li[4]/span/text()')[0]
movie_want=int(movie_want.replace('人想看',''))
# print(movie_want)
#添加信息到列表
movie_info_list.append({
'name':movie_name,
'date':movie_date,
'type':movie_type,
'nation':movie_nation,
'want':movie_want
})
#根據(jù)想看人數(shù)進(jìn)行排序
movie_info_list.sort(key=lambda x : x['want'],reverse=True)
counts={}
# 繪制即將上映電影國家的占比圖(餅圖)
#計(jì)算上映國家的電影片數(shù)
for nation in movie_info_list:
counts[nation['nation']] = counts.get(nation['nation'], 0) + 1
#將字典轉(zhuǎn)換為列表
items = list(counts.items())
print(items)
# 取出繪制餅圖的數(shù)據(jù)和標(biāo)簽
co=[]
lables=[]
for i in range(len(items)):
role, count = items[i]
co.append(count)
lables.append(role)
explode = [0.1, 0, 0, 0]
plt.pie(co, shadow=True,explode=explode, labels=lables, autopct = '%1.1f%%')
plt.legend(loc=2)
plt.axis('equal')
plt.show()
#繪制top5最想看的電影(柱狀圖)
#電影名稱
x = [movie_info_list[i]['name'] for i in range(5)]
# top5 = [movie_info_list[i] for i in range(5)]
# x = [x['name'] for x in top5]
#想看人數(shù)
y = [movie_info_list[i]['want'] for i in range(5)]
# y = [y['want'] for y in top5]
print(x)
print(y)
plt.xlabel('電影名稱')
plt.ylabel('想看人數(shù)(人)')
plt.bar(x, y)
plt.show()
運(yùn)行結(jié)果：
運(yùn)行結(jié)果1
運(yùn)行結(jié)果2
運(yùn)行結(jié)果3
