from lxml import etree html_tree = etree. 구문 분석(' XX.html')pip install lxml ‐i https://pypi.douban.com/simple
导入lxml.etreefrom lxml import etree
etree.parse() 解析本地文件html_tree = etree.parse('XX.html')
etree.HTML() 服务器响应文件html_tree = etree.HTML(response.read().decode('utf‐8')
html_tree = etree.HTML(response.read().decode('utf‐8')
//div[@id] //div[@id="maincontent"]
//@class
//div[contains(@id, "he")] //div[starts‐with(@id, "he")]
//div/h2/text()
xpath.html rreee
//div[@id="head" and @class="s_down"] //title | //price
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8"/>
<title>Title</title>
</head>
<body>
<ul>
<li id="l1" class="class1">北京</li>
<li id="l2" class="class2">上海</li>
<li id="d1">广州</li>
<li>深圳</li>
</ul>
</body>
</html>
from lxml import etree # xpath解析 # 本地文件： etree.parse # 服务器相应的数据 response.read().decode('utf-8') etree.HTML() tree = etree.parse('xpath.html') # 查找url下边的li li_list = tree.xpath('//body/ul/li') print(len(li_list)) # 4 # 获取标签中的内容 li_list = tree.xpath('//body/ul/li/text()') print(li_list) # ['北京', '上海', '广州', '深圳'] # 获取带id属性的li li_list = tree.xpath('//ul/li[@id]') print(len(li_list)) # 3 # 获取id为l1的标签内容 li_list = tree.xpath('//ul/li[@id="l1"]/text()') print(li_list) # ['北京'] # 获取id为l1的class属性值 c1 = tree.xpath('//ul/li[@id="l1"]/@class') print(c1) # ['class1'] # 获取id中包含l的标签 li_list = tree.xpath('//ul/li[contains(@id, "l")]/text()') print(li_list) # ['北京', '上海'] # 获取id以d开头的标签 li_list = tree.xpath('//ul/li[starts-with(@id,"d")]/text()') print(li_list) # ['广州'] # 获取id为l2并且class为class2的标签 li_list = tree.xpath('//ul/li[@id="l2" and @class="class2"]/text()') print(li_list) # ['上海'] # 获取id为l2或id为d1的标签 li_list = tree.xpath('//ul/li[@id="l2"]/text() | //ul/li[@id="d1"]/text()') print(li_list) # ['上海', '广州']
import urllib.request
from lxml import etree
url = 'http://www.baidu.com'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.0.0 Safari/537.36'
}
request = urllib.request.Request(url=url, headers=headers)
response = urllib.request.urlopen(request)
content = response.read().decode('utf-8')
tree = etree.HTML(content)
value = tree.xpath('//input[@id="su"]/@value')
print(value)# 需求 下载的前十页的图片
# https://sc.chinaz.com/tupian/qinglvtupian.html 1
# https://sc.chinaz.com/tupian/qinglvtupian_page.html
import urllib.request
from lxml import etree
def create_request(page):
if (page == 1):
url = 'https://sc.chinaz.com/tupian/qinglvtupian.html'
else:
url = 'https://sc.chinaz.com/tupian/qinglvtupian_' + str(page) + '.html'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36',
}
request = urllib.request.Request(url=url, headers=headers)
return request
def get_content(request):
response = urllib.request.urlopen(request)
content = response.read().decode('utf-8')
return content
def down_load(content):
# 下载图片
# urllib.request.urlretrieve('图片地址','文件的名字')
tree = etree.HTML(content)
name_list = tree.xpath('//div[@id="container"]//a/img/@alt')
# 一般设计图片的网站都会进行懒加载
src_list = tree.xpath('//div[@id="container"]//a/img/@src2')
print(src_list)
for i in range(len(name_list)):
name = name_list[i]
src = src_list[i]
url = 'https:' + src
urllib.request.urlretrieve(url=url, filename='./loveImg/' + name + '.jpg')
if __name__ == '__main__':
start_page = int(input('请输入起始页码'))
end_page = int(input('请输入结束页码'))
for page in range(start_page, end_page + 1):
# (1) 请求对象的定制
request = create_request(page)
# （2）获取网页的源码
content = get_content(request)
# （3）下载
down_load(content)J 사용 SONPath 구문 요소 및 해당 XPath 요소 비교:
예:
jsonpath.json
pip install jsonpath
obj = json.load(open('json文件', 'r', encoding='utf‐8')) ret = jsonpath.jsonpath(obj, 'jsonpath语法')
2 가져오기from bs4 import BeautifulSoup
3. 객체 생성
서버 응답 파일 생성 객체 수프 = BeautifulSoup(response.read().decode(), 'lxml')
로컬 파일 생성 객체 수프 = BeautifulSoup (open('1.html'), 'lxml')
3.2로 지정해야 합니다. 설치 및 생성
3.3 노드 위치 지정{ "store": { "book": [ { "category": "修真", "author": "六道", "title": "坏蛋是怎样练成的", "price": 8.95 }, { "category": "修真", "author": "天蚕土豆", "title": "斗破苍穹", "price": 12.99 }, { "category": "修真", "author": "唐家三少", "title": "斗罗大陆", "isbn": "0-553-21311-3", "price": 8.99 }, { "category": "修真", "author": "南派三叔", "title": "星辰变", "isbn": "0-395-19395-8", "price": 22.99 } ], "bicycle": { "author": "老马", "color": "黑色", "price": 19.95 } } }로그인 후 복사
import json
import jsonpath
obj = json.load(open('jsonpath.json', 'r', encoding='utf-8'))
# 书店所有书的作者
author_list = jsonpath.jsonpath(obj, '$.store.book[*].author')
print(author_list) # ['六道', '天蚕土豆', '唐家三少', '南派三叔']
# 所有的作者
author_list = jsonpath.jsonpath(obj, '$..author')
print(author_list) # ['六道', '天蚕土豆', '唐家三少', '南派三叔', '老马']
# store下面的所有的元素
tag_list = jsonpath.jsonpath(obj, '$.store.*')
print(
tag_list) # [[{'category': '修真', 'author': '六道', 'title': '坏蛋是怎样练成的', 'price': 8.95}, {'category': '修真', 'author': '天蚕土豆', 'title': '斗破苍穹', 'price': 12.99}, {'category': '修真', 'author': '唐家三少', 'title': '斗罗大陆', 'isbn': '0-553-21311-3', 'price': 8.99}, {'category': '修真', 'author': '南派三叔', 'title': '星辰变', 'isbn': '0-395-19395-8', 'price': 22.99}], {'author': '老马', 'color': '黑色', 'price': 19.95}]
# store里面所有东西的price
price_list = jsonpath.jsonpath(obj, '$.store..price')
print(price_list) # [8.95, 12.99, 8.99, 22.99, 19.95]
# 第三个书
book = jsonpath.jsonpath(obj, '$..book[2]')
print(book) # [{'category': '修真', 'author': '唐家三少', 'title': '斗罗大陆', 'isbn': '0-553-21311-3', 'price': 8.99}]
# 最后一本书
book = jsonpath.jsonpath(obj, '$..book[(@.length-1)]')
print(book) # [{'category': '修真', 'author': '南派三叔', 'title': '星辰变', 'isbn': '0-395-19395-8', 'price': 22.99}]
# 前面的两本书
book_list = jsonpath.jsonpath(obj, '$..book[0,1]')
# book_list = jsonpath.jsonpath(obj,'$..book[:2]')
print(
book_list) # [{'category': '修真', 'author': '六道', 'title': '坏蛋是怎样练成的', 'price': 8.95}, {'category': '修真', 'author': '天蚕土豆', 'title': '斗破苍穹', 'price': 12.99}]
# 条件过滤需要在（）的前面添加一个？
# 过滤出所有的包含isbn的书。
book_list = jsonpath.jsonpath(obj, '$..book[?(@.isbn)]')
print(
book_list) # [{'category': '修真', 'author': '唐家三少', 'title': '斗罗大陆', 'isbn': '0-553-21311-3', 'price': 8.99}, {'category': '修真', 'author': '南派三叔', 'title': '星辰变', 'isbn': '0-395-19395-8', 'price': 22.99}]
# 哪本书超过了10块钱
book_list = jsonpath.jsonpath(obj, '$..book[?(@.price>10)]')
print(
book_list) # [{'category': '修真', 'author': '天蚕土豆', 'title': '斗破苍穹', 'price': 12.99}, {'category': '修真', 'author': '南派三叔', 'title': '星辰变', 'isbn': '0-395-19395-8', 'price': 22.99}]1.根据标签名查找节点 soup.a 【注】只能找到第一个a soup.a.name soup.a.attrs 2.函数 (1).find(返回一个对象) find('a')：只找到第一个a标签 find('a', title='名字') find('a', class_='名字') (2).find_all(返回一个列表) find_all('a') 查找到所有的a find_all(['a', 'span']) 返回所有的a和span find_all('a', limit=2) 只找前两个a (3).select(根据选择器得到节点对象)【推荐】 1.element eg:p 2..class eg:.firstname 3.#id eg:#firstname 4.属性选择器 [attribute] eg:li = soup.select('li[class]') [attribute=value] eg:li = soup.select('li[class="hengheng1"]') 5.层级选择器 element element div p element>element div>p element,element div,p eg:soup = soup.select('a,span')
1.根据标签名查找节点 soup.a 【注】只能找到第一个a soup.a.name soup.a.attrs 2.函数 (1).find(返回一个对象) find('a')：只找到第一个a标签 find('a', title='名字') find('a', class_='名字') (2).find_all(返回一个列表) find_all('a') 查找到所有的a find_all(['a', 'span']) 返回所有的a和span find_all('a', limit=2) 只找前两个a (3).select(根据选择器得到节点对象)【推荐】 1.element eg:p 2..class eg:.firstname 3.#id eg:#firstname 4.属性选择器 [attribute] eg:li = soup.select('li[class]') [attribute=value] eg:li = soup.select('li[class="hengheng1"]') 5.层级选择器 element element div p element>element div>p element,element div,p eg:soup = soup.select('a,span')
(1).获取节点内容：适用于标签中嵌套标签的结构 obj.string obj.get_text()【推荐】 (2).节点的属性 tag.name 获取标签名 eg:tag = find('li) print(tag.name) tag.attrs将属性值作为一个字典返回 (3).获取节点属性 obj.attrs.get('title')【常用】 obj.get('title') obj['title']
(1).获取节点内容：适用于标签中嵌套标签的结构 obj.string obj.get_text()【推荐】 (2).节点的属性 tag.name 获取标签名 eg:tag = find('li) print(tag.name) tag.attrs将属性值作为一个字典返回 (3).获取节点属性 obj.attrs.get('title')【常用】 obj.get('title') obj['title']
3.7 스타벅스 제품명 파싱<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>Title</title>
</head>
<body>
<div>
<ul>
<li id="l1">张三</li>
<li id="l2">李四</li>
<li>王五</li>
<a href="" id=" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" " class="a1">google</a>
<span>嘿嘿嘿</span>
</ul>
</div>
<a href="" title=" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" a2">百度</a>
<div id="d1">
<span>
哈哈哈
</span>
</div>
<p id="p1" class="p1">呵呵呵</p>
</body>
</html>
위 내용은 xpath, JsonPath 및 bs4에 Python을 사용하는 방법은 무엇입니까?의 상세 내용입니다. 자세한 내용은 PHP 중국어 웹사이트의 기타 관련 기사를 참조하세요!
![[웹 프런트엔드] Node.js 빠른 시작](https://img.php.cn/upload/course/000/000/067/662b5d34ba7c0227.png)
