利用Python爬取网页内容

时间：04-07来源：作者：点击数：36

一、爬取简单的网页

1、打开cmd

2、安装requests模块，输入pip install requests

3、新建一个.py文件，我们以https://www.bqkan.com这个网站为例，以下是爬取斗罗大陆的网页

import requests  # 导入requests包

url = 'https://www.bqkan.com/3_3026/1343656.html'
strHtml = requests.get(url)  # Get方式获取网页数据
html = strHtml.text
print(html)

二、爬取小说的某一章节

1、打开cmd，安装Beautiful Soup，输入pip install beautifulsoup4

2、对爬取出来的数据进行数据清洗，代码如下：

# 爬虫爬取网页
import requests  # 导入requests包
from bs4 import BeautifulSoup

url = 'https://www.bqkan.com/3_3026/1343656.html'
strHtml = requests.get(url)  # Get方式获取网页数据
html = strHtml.text
bf = BeautifulSoup(html,"html.parser")
texts = bf.find_all('div', class_='showtxt')
print(texts[0].text.replace('\xa0'*8,'\n\n'))

三、爬取整本小说

以斗罗大陆 URL=https://www.bqkan.com/3_3026/为例：

1、打开审查元素 F12，我们发现这些章节都存在于div标签下的class属性为listmain中，并且都是通过和https://www.bqkan.com/3_3026进行拼接的网址：

2、于是，我们修改原有代码，如下图所示，就可以获得所有章节的href中的地址：

import requests  # 导入requests包
from bs4 import BeautifulSoup

url = 'https://www.bqkan.com/3_3026'
strHtml = requests.get(url)  # Get方式获取网页数据
html = strHtml.text
bf = BeautifulSoup(html,"html.parser")
div = bf.find_all('div', class_='listmain')
print(div[0])

3、通过Beautiful Soup对数据进行清洗，获得每个章节的完整链接，代码如下：

import requests  # 导入requests包
from bs4 import BeautifulSoup

source = "https://www.bqkan.com/"
url = 'https://www.bqkan.com/3_3026'
strHtml = requests.get(url)  # Get方式获取网页数据
html = strHtml.text
bf = BeautifulSoup(html, "html.parser")
div = bf.find_all('div', class_='listmain')
a_bf = BeautifulSoup(str(div[0]), "html.parser")
a = a_bf.find_all("a")
for item in a:
    print(item.string, source + item.get("href"))

4、获得到了每一章的完整链接，于是我们可以对该小说进行完整下载了，代码如下：

from bs4 import BeautifulSoup
import requests


class downloader(object):

    # 初始化
    def __init__(self):
        self.server = 'http://www.biqukan.com'
        self.target = 'https://www.bqkan.com/3_3026'
        self.names = []  # 存放章节名
        self.urls = []  # 存放章节链接
        self.nums = 0  # 章节数

    # 获取完整章节地址
    def get_download_url(self):
        req = requests.get(url=self.target)
        html = req.text
        div_bf = BeautifulSoup(html, "html.parser")
        div = div_bf.find_all('div', class_='listmain')
        a_bf = BeautifulSoup(str(div[0]), "html.parser")
        a = a_bf.find_all("a")
        self.nums = len(a)  # 统计章节数
        for each in a:
            print(each.string,self.server + each.get('href'))
            self.names.append(each.string)
            self.urls.append(self.server + each.get('href'))

    # 获取对应链接的地址
    def get_contents(self, target):
        req = requests.get(url=target)
        html = req.text
        bf = BeautifulSoup(html, "html.parser")
        texts = bf.find_all('div', class_='showtxt')
        texts = texts[0].text.replace('\xa0' * 8, '\n\n')
        return texts

    # 将内容写入磁盘中
    def writer(self, name, path, text):
        write_flag = True
        with open(path, 'w', encoding='utf-8') as f:
            f.write(name + '\n')
            f.writelines(text)
            f.write('\n\n')


if __name__ == "__main__":
    dl = downloader()
    dl.get_download_url()
    print('《斗罗大陆》开始下载：')
    for i in range(dl.nums):
        print("正在下载=>", dl.names[i])
        dl.writer(dl.names[i], 'E:\\斗罗大陆\\' + dl.names[i] + '.txt', dl.get_contents(dl.urls[i]))
    print('《斗罗大陆》下载完成!')