Python爬取小说(2)单章节爬取

#coding = utf-8
#urlopen:打开网址
#Request:请求
from urllib.request import urlopen,Request
#导入gzip包:解压gzip
import gzip
import ssl
ssl._create_default_https_context = ssl._create_unverified_context()

from lxml import etree

path = "http://www.xbiquge.la/10/10489/4535761.html"
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36',
    "Accept-Encoding": "gzip, deflate",
    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
    "Accept-Language":"zh-CN,zh;q=0.9"
}
#封装请求
req = Request(url=path,headers=headers)
#打开链接
conn = urlopen(req)
#判断是否正常打开
if conn.code == 200:
    #获取数据
    data = conn.read()
    #print(type(data))
    #因为我们下载的是压缩的网页 下面是解压缩
    data = gzip.decompress(data).decode("utf-8")
    #转换编码格式 (如果没有经过gzip格式压缩,用这个)
    # data = data.decode(encoding="utf-8")
    html = etree.HTML(data)
    #获取对应节点内容 如获取一个id为content的div的内容区的内容
    text = html.xpath("//div[@id='content']/text()")
    #整理字符串格式
    text = "".join(text)
    #去除行
    text = text.split()
    #拼接
    text = "\n".join(text)
    print(text)
else:
    print("网址有问题")

来源：CSDN

作者：奋斗才是人生基调

链接：https://blog.csdn.net/weixin_42735156/article/details/103833666

标签

gzip

data

python