學(xué)習(xí)Python第四天
爬蟲
大數(shù)據(jù) 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
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)容黎炉，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)枝秤、
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)
requests
導(dǎo)入
import requests
url = 'https://www.baidu.com'
url = 'https://www.taobao.com/'
url = 'http://www.dangdang.com/'
response = requests.get(url)
print(response)
獲取str類型的響應(yīng)
print(response.text)
獲取bytes類型的響應(yīng)
print(response.content)
獲取響應(yīng)頭
print(response.headers)
獲取狀態(tài)碼
print(response.status_code)
print(response.encoding)
200 ok 404 500
沒有添加請求頭的知乎網(wǎng)站
resp = requests.get('https://www.zhihu.com/')
print(resp.status_code)
使用字典定義請求頭
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('https://www.zhihu.com/', headers = headers)
print(resp.status_code)
import requests
from lxml import html
def spider_dangdang(isbn):
# 目標(biāo)站點地址
url = 'http://search.dangdang.com/?key={}&act=input'.format(isbn)
print(url)
# 獲取站點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)
# 圖書價格
price = li.xpath('./p[@class="price"]/span[@class="search_now_price"]/text()')[0]
price = float(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)
spider_dangdang('9787115428028')
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)站點地址
url = 'http://search.dangdang.com/?key={}&act=input'.format(isbn)
print(url)
# 獲取站點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('您好拜隧，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)
# 圖書價格
price = li.xpath('./p[@class="price"]/span[@class="search_now_price"]/text()')[0]
price = float(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)
# 添加每一個商家的圖書信息
book_list.append({
'title':title,
'price':price,
'link':link,
'store':store
})
# 按照價格進(jìn)行排序
book_list.sort(key=lambda x:x['price'])
# 遍歷booklist
for book in book_list:
print(book)
# 展示價格最低的前10家 柱狀圖
# 店鋪的名稱
top10_store = [book_list[i] for i in range(10)]
x = []
for store in top10_store:
x.append(store['store'])
x = [x['store'] for x in top10_store]
print(x)
# 圖書的價格
y = [x['price'] for x in top10_store]
print(y)
# plt.bar(x, y)
plt.barh(x, y)
plt.show()
# 存儲成csv文件
df = pd.DataFrame(book_list)
df.to_csv('dangdang.csv')
spider_dangdang('9787115428028')
