python的lxml解析器

Posted 2020-11-19 timxgb

from lxml import etree

import codecs
import sys
from lxml import etree

def parser(p):
    tree = etree.HTML(open(str(p)+‘.html‘, ‘r‘).read())
    
    nodes = tree.xpath("//div[@class=‘BlueTable‘]//tr")
    #nodes = tree.xpath("//text()")
    for n in nodes:
        #mystr=etree.tostring(n,pretty_print=True)
        mystr=etree.tostring(n, method="html")
        print(etree.HTML(mystr).xpath("//text()"))

for p in range(1,211):
    parser(p);