python爬虫html解析器_Python爬虫如何解析此类html?

1.re模块本质属于对字符串的强制提取

解析方法有

html = """

哈哈

你真

搞笑

"""

# 使用 scrapy 中的 Selector 进行解析

from scrapy import Selector

response = Selector(text=html)

text_list = response.css("div *::text").getall()

print([i for i in text_list if i.replace("\n", "")])

url = response.css("div img::attr(src)").get()

print(url)

"""

结果

['哈哈', '你真', '搞笑']

www.baidu.com

"""

# 使用 BeautifulSoup 进行解析

from bs4 import BeautifulSoup

soup = BeautifulSoup(html, 'lxml')

haha = soup.div.p.string

print(haha)

url = soup.img.attrs['src']

print(url)

nizhen = soup.div.get_text()[3:-3]

print(nizhen)

gaoxiao = soup.div.find_all('p')[-1].string

print(gaoxiao)

print(haha, url, nizhen, gaoxiao)

"""

结果

哈哈

www.baidu.com

你真

搞笑

哈哈 www.baidu.com 你真 搞笑

"""

# 使用lxml进行解析

from lxml import etree

html = etree.HTML(html) # 初始化生成一个XPath解析对象

text_lists = html.xpath("//div//text()")

print([i for i in text_lists if i.replace("\n", "")])

url = html.xpath("//div/p/img/@src")

print(url)

"""

结果

['哈哈', '你真', '搞笑']

['www.baidu.com']

"""

还可以解析的模块有

pyquery re 等等