如何爬取网页
看这是我代码
去博客设置页面,选择一款你喜欢的代码片高亮样式,下面展示同样高亮的 代码片
.
import requests
from lxml import etree
url=‘https://www.jhc.cn/4548/list.htm’
url1=‘https://www.jhc.cn’
html=requests.get(url)
html.encoding=‘utf-8’
s=etree.HTML(html.text)
print(html)
title=s.xpath(’//[@id=“wp_news_w9”]/ul//span[2]/a’)
href=s.xpath(’//[@id=“wp_news_w9”]/ul//span[2]/a/@href’)
for i in range(0,len(title)):
print(title[i].text,url1 + href[i])
for a in range(0,len(href)):
url1_href = url1 + href[a]
print(url1_href)
html = requests.get(url1_href)
html.encoding = ‘utf-8’
s = etree.HTML(html.text)
title=s.xpath(’/html/body/div[2]/div/div[1]/div/h1’)
time=s.xpath(’/html/body/div[2]/div/div[1]/div/p/span[3]’)
context=s.xpath("/html/body/div[2]/div/div[1]/div/div[2]/article/div/p/span/text()")
for c in range(0,len(title)):
print(title[c].text,time[c].text)
o=title[c].text+time[c].text
f = open(“d.txt”, “a”)
f.write(o)
f.close()
for d in range(0,len(context)):
if context[d].strip()!=’’:
print(context[d])
e=str(context[d])
f = open(“d.txt”, “a”,encoding=‘utf-8’)
f.write(e)
f.close()