简单静态单页面爬虫

引入requests库后，使用get方法，返回网页的状态，打印此时网页是否回应（获取成功）

response = requests.get('https://www.37zww.net/0/234/208873.html')
print(response.status_code)

如果返回200（输出为200）则获取成功

完整代码如下：

import requests
#解法一

from pyquery import PyQuery as pq

#爬取单个页面
response = requests.get('https://www.37zww.net/0/234/208873.html')
print(response.status_code)
#
# type(response)
# response.headers
#将网页的编码改变，以免乱码
response.encoding = "GB2312"
# response.apparent_encoding
# response.text

doc = pq(response.text)#获取网页的文本形式
title = doc('.bookname > h1').text()
print(title)
content = doc('#content').text()
print(content)
#将获取的文本内容写入txt
with open ('剑来.txt',mode = 'w+',encoding='utf-8') as f:
    f.write(title)
    f.write('\n')
    f.write(content)
    f.write('\n')

#简单多章小说爬取 完整代码如下：

response = requests.get('https://www.37zww.net/0/234/')
response.encoding = response.apparent_encoding
doc = pq(response.text)
links = doc('#list>dl>dd>a')
for link in links.items():
    print("https://www.37zww.net/0/234/"+link.attr.href)
    response  = requests.get("https://www.37zww.net/0/234/"+link.attr.href)
    response.encoding=response.apparent_encoding
    doc = pq(response.text)
    title = doc('.bookname>h1').text()
    content = doc('#content').text()
    with open ('剑来.txt',mode = 'a+',encoding='utf-8')as f:
        f.write(title)
        f.write('\n')
        f.write(content)
        f.write('\n')