# 1.xpath解析原理:
# 通过需要的标签在html/xml结构的标签路径去获取指定标签
# 2.xml数据格式
# xml和json一样是一种通用的数据格式,用于多语言程序之间的数据传输
# xml和json的比较:xml(更安全,方便加密)、json更轻量级(传输的时候更快)
# xml和html一样是以节点(标签)为基本单位来提供数据的,例如:
"""
保存一个商店中的书的信息:
json:
{
name: '新华书店',
books: [
{
name: '流程的Python'
author: '张三'
price: 120
num: 20
},
{
name: '代码整洁之道'
author: '小明'
price: 89
num: 12
},
{
name: '程序员修养之道- 从小工到专家'
author: 'Bob'
price: 78
num:23
},
{
name: 'Unix编程艺术'
author: '小花'
price: 102
num: 9
}
]
}
<bookStore>
<name>新华书店</name>
<books>
<book>
<name flag="hot">流程的Python</name>
<author>张三</author>
<price>120</price>
<num>20</num>
</book>
<book>
<name>代码整洁之道</name>
<author>小明</author>
<price>89</price>
<num>12</num>
</book>
<book>
<name>程序员修养之道- 从小工到专家</name>
<author>Bob</author>
<price>78</price>
<num>23</num>
</book>
<book>
<name>Unix编程艺术</name>
<author>小花</author>
<price>102</price>
<num>9</num>
</book>
</books>
</bookStore>
"""
from lxml import etree
with open('data.xml', encoding='utf-8') as f:
data = f.read()
# 1.获取树对应的根节点
# 树 - 整个xml/html
# 根节点 - xml或者html数据中最外层的标签/节点
bookStore = etree.XML(data)
print(bookStore)
# 2.通过xPath解析数据
# 语法: 节点对象.xpath(路径)
# =======================1)路径的写法=========================
# 1) / - 从根节点开始的绝对路径(查找的时候跟前面的节点对象没有任何关系)
# /A/B - 找根节点A下面的B(A如果不是根节点,就找不到)
result = bookStore.xpath('/bookStore/books/book/author')
print(result)
result = bookStore.xpath('/bookStore/name')
print(result) # [<Element name at 0x10cfc0be0>]
book_list = bookStore.xpath('/bookStore/books/book')
print(book_list)
book_list = result[0].xpath('/bookStore/books/book')
print(book_list)
# 2) // - 从任意位置开始按路径查找
# //A/B - 在整个xml或者html中找A节点下面的B节点
# //B - 在整个xml或者html中找B节点
name_list = bookStore.xpath('//name')
print(name_list)
name_list = bookStore.xpath('//book/name')
print(name_list)
# 3)
# ./ - 从当前位置开始找
# 节点名称 - 从当前位置开始找
name_list = bookStore.xpath('./name')
print(name_list)
name_list = bookStore.xpath('./books/book/name')
print(name_list)
result = book_list[0].xpath('./name/text()')
print(result)
result = book_list[0].xpath('name/text()')
print(result)
# 4) ../ - 从当前节点的父节点开始查找
name_list = bookStore.xpath('//name')
name_1 = name_list[0]
result = name_1.xpath('..')
print(result) # [<Element bookStore at 0x106d2c050>]
result = name_1.xpath('../books')
print(result) # [<Element books at 0x105461190>]
# ======================2)标签内容和属性=================
# 1)text() - 获取标签内容
store_name = bookStore.xpath('/bookStore/name/text()')
print(store_name) # ['新华书店']
store_name = bookStore.xpath('//name')[0].xpath('./text()')
print(store_name) # ['新华书店']
result = bookStore.xpath('//text()')
print(result)
# 2)@属性名 - 获取指定属性值
flag = bookStore.xpath('//book/name')[0].xpath('./@flag')
print(flag) # ['hot']
ids = bookStore.xpath('//book/@id')
print(ids) # ['b1', 'b2', 'b3', 'b4']
# 3)======================3)谓词==================
# 路径[谓词] - 按照谓词对应的条件通过指定路径获取标签
# 1)[N] - 获取第N个标签,从1开始
# //book[1]/name - 第一本书下面的name
# //book/name[1] - 所有的书后面的第一个name
name_1 = bookStore.xpath('//book[1]/name/text()')
print(name_1) # ['流程的Python']
# 2)
# [last()] - 获取最后一个标签
# [last()-N] - 获取最后一个的前N个标签(获取倒数第 N+1 个标签)
name_last = bookStore.xpath('//book[last()]/name/text()')
print(name_last) # ['Unix编程艺术']
name_last_2 = bookStore.xpath('//book[last()-1]/name/text()')
print(name_last_2)
# 3)
# [position()<N] - 获取前N-1个标签
# [position()>N] - 获取第N个以后的标签
book_list = bookStore.xpath('//books/book[position()<4]/author/text()')
print(book_list) # ['张三', '小明', 'Bob']
book_list = bookStore.xpath('//books/book[position()>2]/author/text()')
print(book_list) # ['Bob', '小花']
# 4) [@属性名] - 获取拥有指定属性的标签
flags = bookStore.xpath('//name[@flag]/text()')
print(flags) # ['流程的Python', '代码整洁之道']
# 5) [@属性名=值] - 获取指定属性是指定值的标签
flags = bookStore.xpath('//name[@flag="hot"]/text()')
print(flags) # ['流程的Python']
# [@属性名>数值]、[@属性名<数值]、[@属性名>=数值]、[@属性名<=数值]
book_list = bookStore.xpath('//books/book[@id>200]')
print(book_list)
# 6) [标签名=值]、[标签名>数值]、[标签名>=数值]、[标签名<数值]、[标签名<=数值]
# //book[name="流程的Python"] - 获取子标签name标签值是 '流程的Python'的 book标签
book_list = bookStore.xpath('//book[name="流程的Python"]')
print(book_list) # [<Element book at 0x10495a280>]
book_list = bookStore.xpath('//book[price>100]/name/text()')
print(book_list) # ['流程的Python', 'Unix编程艺术']
# ==================4)通配符==========================
# * - 表示任意节点或者任意属性(不能表示任意值)
# //book[1]/* - 获取第一个book节点中所有的子节点
result = bookStore.xpath('//book[1]/*/text()')
print(result)
# //*[@id] - 获取设置了id属性的任意节点
result = bookStore.xpath('//*[@id]')
print(result)
# //*[@*] - 获取所有设置了属性的节点
result = bookStore.xpath('//*[@*]')
print(result)
result = bookStore.xpath('//book[@id=100]')
print(result)
# ==================5)选取若干路径(分支)=================
# 路径1 | 路径2 | 路径3 | ... - 同时选取每个路径对应的标签
# 注意:谓词不能使用分支
result = bookStore.xpath('//book[1]/name/text()|//book[1]/price/text()')
print(result)
from lxml import etree
import requests
def get_data():
url = 'https://movie.douban.com/top250'
headers = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.111 Safari/537.36'
}
response = requests.get(url, headers=headers)
if response.status_code == 200:
xpath_analysis(response.text)
else:
print('请求失败!', response)
def xpath_analysis(data):
html = etree.HTML(data)
# 获取电影盒子
li_list = html.xpath('//ol[@class="grid_view"]/li')
all_f_info = []
# 遍历拿到每个电影对应的盒子(li标签)
for li in li_list:
f_info = {}
# 1.电影名
names = li.xpath('./div/div[@class="info"]/div[@class="hd"]/a/span/text()')
# print(names)
f_info['name'] = names[0]
# 2.导演
director = li.xpath('./div/div[@class="info"]/div[@class="bd"]/p[1]/text()')
# 字符串.strip() - 去掉字符串开头和结尾的空白字符
director = [x.strip() for x in director]
# print(director)
f_info['director'] = director[0]
f_info['time_type'] = director[1]
# print(f_info)
# 3.评分
score = li.xpath('./div/div[@class="info"]/div[@class="bd"]/div/span[@class="rating_num"]/text()')
f_info['score'] = score[0]
# print(f_info)
all_f_info.append(f_info)
print(all_f_info)
if __name__ == '__main__':
get_data()
import csv
def write_data1():
# ===============写列表数据========================
# 1.打开文件
# 参数newline在csv文件中必须添加
with open('files/data1.csv', 'w', newline='')as f:
# 2.创建writer对象
# csv.writer(文件对象)
writer = csv.writer(f)
# 3.写数据
# 一行一行的写
writer.writerow(['姓名', '性别', '年龄', '电话'])
# 一次写多行
writer.writerows([
['张三', '男', '30', '123'],
['李四', '女', '22', '321']
])
def write_data2():
# ====================将数据以字典的形式写入文件===================
# 1.打开文件
with open('files/data2.csv', 'w', encoding='utf-8', newline='') as f:
# 2.创建writer
# csv.DictWriter(文件对象, 表头列表)
# 表头列表必须是要写入的字典的所有的key
writer = csv.DictWriter(f, ['name', 'sex', 'age', 'tel'])
# 将表头列表中的元素作为文件的第一行内容
writer.writeheader()
# 一行一行的写
writer.writerow({
'name': '张三',
'sex': '男',
'age': 30,
'tel': '110'
})
# 一次写多行
writer.writerows([
{'name': '小明', 'sex': '男', 'age': 19, 'tel': '119'},
{'name': '小红', 'sex': '女', 'age': 21, 'tel': '114'}
])
write_data2()
def reader_list():
# ===================以列表的形式读====================
# 1.打开文件
with open('files/data1.csv', encoding='gbk', newline='') as f:
# 2. 创建reader
reader = csv.reader(f)
print(reader)
# 3.一行一行的获取数据
# 获取每一行的内容和迭代器获取元素的方法一样
print(next(reader))
print(next(reader))
print('============')
for x in reader:
print(x)
def reader_dict():
# ===================以字典的形式读====================
# 1.打开文件
with open('files/data1.csv', encoding='gbk', newline='') as f:
# 2.创建reader
# csv.DictReader(文件对象, 字典的key列表)
# 字典的key列表 - 不赋值的时候会把第一行的内容作为字典的key
reader = csv.DictReader(f, ['name', 'sex', 'age', 'tel'])
# 3.读数据
next(reader)
print(dict(next(reader)))
for x in reader:
print(dict(x))
reader_dict()