解析库-LXML
pip install -i https://pypi.tuna.tsinghua.edu.cn/simple lxml
使用解析规则：XPath
| 表达式 | 描述 |
|---|---|
| nodename | 选取此节点的所有子节点 |
| / | 从当前节点，选取直接子节点 |
| // | 从当前节点，选取所有子孙节点 |
| . | 选取当前节点 |
| .. | 选取当前节点的父节点 |
| @ | 选取属性 |
构建实例
从文本构建
def load_text():
text = '''
'''
html = etree.HTML(text)
result = etree.tostring(html)
print(result.decode("utf-8"))
从文件构建
def load_text2():
html = etree.parse("./test.html", etree.HTMLParser())
result = etree.tostring(html)
print(result.decode("utf-8"))
注意
etree.toString()返回的是bytes类型，需要调用decode方法将其转换成String类型
经过处理后的html代码，会被自动修复，添加缺少的标签
选中所有节点
要选中某个类型的所有节点，以 // 开头就可以了
# 选中所有节点
html = etree.parse("./test.html", etree.HTMLParser())
results = html.xpath("//*")
print(results)
# 选中所有的li节点
results = html.xpath("//li")
print(results)
print(results[0])
选中所有子节点
# 选中直接子节点
html = etree.parse("./test.html", etree.HTMLParser())
result = html.xpath("//li/a")
print(result)
选中所有子孙节点
# 选取所有子孙节点
result = html.xpath("//li//a")
print(result)
选取父亲节点
def select_parent_nodes():
html = etree.parse("./test.html", etree.HTMLParser())
# 选中属性href='link4.html'的a标签的直接父亲
result = html.xpath("//a[@href='link4.html']/..")
print(result)
# 选中属性href='link4.html'的a标签的父亲的class属性
result = html.xpath("//a[@href='link4.html']/../@class")
print(result)
# 使用parent::选中父亲
result = html.xpath("//a[@href='link4.html']/parent::*/@class")
print(result)
test.html
按属性选择
def select_node_by_attrs():
html = etree.parse("./test.html", etree.HTMLParser())
result = html.xpath("//li[@class='item-0']")
print(result)
获取节点文本
def get_text():
html = etree.parse("./test.html", etree.HTMLParser())
print(etree.tostring(html).decode("utf-8"))
# 使用/获取自身的文本内容
result = html.xpath("//li[@class='item-0']/text()")
print(result) # ['\r\n\t']
# 使用//获取子孙的文本和自己的文本
result = html.xpath("//li[@class='item-0']//text()")
print(result) # ['first item', 'fifth item', '\r\n\t']
获取属性的值
def get_attr_content():
html = etree.parse("./test.html", etree.HTMLParser())
result = html.xpath("//li/a/@href")
print(result)
多值属性匹配
使用contains函数
def get_multi_attr_content():
text = '''
first item
'''
html = etree.HTML(text)
result = html.xpath("//li[@class='li']/a/text()")
print(result)# []
result = html.xpath("//li[contains(@class, 'li')]/a/text()")
print(result)# ['first item']
多属性匹配
def get_multi_attr_match():
text = '''
first item
'''
html = etree.HTML(text)
result = html.xpath("//li[contains(@class, 'li') and @name='item']/a/text()")
print(result)# ['first item']
and 是xpath中的运算符
| 运算符 | 描述 | 实例 |
|---|---|---|
| or | 或 | age=19 or age=20 |
| and | 与 | age>19 and age<21 |
| mod | 取余 | 5 mod 2 |
| 计算两个节点集 | //book | //cd 返回所有拥有book和cd元素的节点集 | |
| + | 加法 | 6+4 |
| - | 减法 | 6-4 |
| * | 乘法 | 6*4 |
| div | 除法 | 6 div 3 |
| = | 等于 | age=19 |
| != | 不等于 | age!=19 |
| < | 小于 | age<19 |
| <= | 小于或等于 | age<=19 |
| > | 大于 | age>19 |
| >= | 大于或等于 | age>=19 |
按顺序选取节点
def select_node_by_order():
html = etree.parse("./test.html", etree.HTMLParser())
# 选取第一个节点
result = html.xpath("//li[1]/a/text()")
print(result)
# 选取最后一个节点
result = html.xpath("//li[last()]/a/text()")
print(result)
# 选取前两个节点
result = html.xpath("//li[position()<3]/a/text()")
print(result)
# 选取倒数第三个节点
result = html.xpath("//li[last()-2]/a/text()")
print(result)
image.png
各种查询
def select_node_by_axies():
text = '''
'''
html = etree.HTML(text)
# 指定元素所有祖先
result = html.xpath("//li[1]/ancestor::*")
print(result)
# 输出[, , , ]
# 指定元素所有div祖先
result = html.xpath("//li[1]/ancestor::div")
print(result)
# 获取所有属性值
result = html.xpath("//li[1]/attribute::*")
print(result)
# 找到直接子节点中满足条件的元素
result = html.xpath("//li[1]/child::a[@href='link1.html']")
print(result)
# 找到所有的后代元素
result = html.xpath("//li[1]/descendant::*")
print(result)
# 找到后低元素的span
result = html.xpath("//li[1]/descendant::span")
print(result)
# 获取该节点后面的兄弟节点以及兄弟节点的子孙节点
result = html.xpath("//li[1]/following::*")
print(result)
# 获取该节点后面的兄弟节点以及兄弟节点的子孙节点的第一个节点
result = html.xpath("//li[1]/following::*[1]")
print(result)
# 获取该节点后面的所有兄弟节点
result = html.xpath("//li[1]/following-sibling::*")
print(result)
image.png
爬取百度贴吧图片
校花吧
获取网页源码
BaiduTieBa.py
import requests
class BaiduTieBa:
def __init__(self,name,pn):
self.name = name
self.url = 'http://tieba.baidu.com/f?kw={}&ie=utf-8&pn='.format(name)
self.headers = {
'User-Agent': 'Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0)'
}
self.url_list = [self.url + str(n * 50) for n in range(pn)]
print(self.url_list)
def get_data(self,url):
r = requests.get(url, headers=self.headers)
return r.content
def save_data(self,data,num):
file_name = self.name + "_" + str(num) + ".html"
with open(file_name,'wb') as f:
f.write(data)
def run(self):
for url in self.url_list:
data = self.get_data(url)
num = self.url_list.index(url)
self.save_data(data,num)
import sys
if __name__ == '__main__':
name = sys.argv[1]
pn = int(sys.argv[2])
baidu = BaiduTieBa(name, pn)
baidu.run()
输入命令行
python BaiduTieBa.py 校花 5
image.png
get_photo.py
from lxml import etree
import requests
class DownloadPhoto:
def __init__(self):
pass
def down_load_img(self,url):
r = requests.get(url)
index = url.rfind("/")
file_name = url[index+1:]
save_name = './photo/' + file_name
print("下载图片" + save_name)
with open(save_name, 'wb') as f:
f.write(r.content)
def parse_photo_url(self, page):
html = etree.parse(page,etree.HTMLParser())
nodes = html.xpath("//a[contains(@class,'thumbnail')]/img/@bpic")
for node in nodes:
self.down_load_img(node)
if __name__ == '__main__':
down = DownloadPhoto()
file_name = ["校花_0.html","校花_1.html","校花_2.html","校花_3.html","校花_4.html"]
for url in file_name:
down.parse_photo_url(url)
run此方法
image.png
image.png
注意使用老版本的请求头，可以在ie中调整版本获取