因为正则表达式本身有难度，所以在这里为大家介绍一下 bs4 实现数据解析。除此之外还有 xpath 解析。因为 xpath 不仅可以在 python 中使用，所以 bs4 和 正则解析一样，仅仅是简单地写两个案例（爬取可翻页的图片，以及爬取三国演义）。以后的重点会在 xpath 上。
闲话少说，我们先来安装 bs4 相关的外来库。比较简单。
1.首先打开 cmd 命令面板，依次安装bs4 和 lxml。
2. 命令分别是 pip install bs4 和 pip install lxml 。
3. 安装完成后我们可以试着调用他们，看看会不会报错。
因为本人水平有限，所以如果出现报错，兄弟们还是百度一下好啦。（总不至于 cmd 命令打错了吧 ~~）
闲话少说，先简单介绍一下 bs4 的用法。
import requests
from bs4 import BeautifulSoup
import os
if __name__ == "__main__":
# 创建文件夹
if not os.path.exists("./糗图（bs4）"):
os.mkdir("./糗图（bs4）")
# UA伪装
header = {
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.72 Safari/537.36"
}
# 指定 url
for i in range(1, 3): # 翻两页
url = "https://www.qiushibaike.com/imgrank/page/%s/" % str(i)
# 获取源码数据
page = requests.get(url = url, headers = header).text
# 数据解析
soup = BeautifulSoup(page, "lxml")
data_list = soup.select(".thumb > a")
for data in data_list:
url = data.img["src"]
title = url.split("/")[-1]
new_url = "https:" + url
photo = requests.get(url = new_url, headers = header).content
# 存储
with open("./糗图（bs4）/" + title, "wb") as fp:
fp.write(photo)
print(title, "下载完成！！！")
print("over!!!")
import requests
from bs4 import BeautifulSoup
if __name__ == "__main__":
# UA 伪装
header = {
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36"
}
# URL
url = "http://sanguo.5000yan.com/"
# 请求命令
page_text = requests.get(url = url, headers = header)
page_text.encoding = "utf-8"
page_text = page_text.text
soup = BeautifulSoup(page_text, "lxml")
# bs4 解析
li_list = soup.select(".sidamingzhu-list-mulu > ul > li")
for li in li_list:
print(li)
new_url = li.a["href"]
title = li.a.text
# 新的请求命令
response = requests.get(url = new_url, headers = header)
response.encoding = "utf-8"
new_page_text = response.text
new_soup = BeautifulSoup(new_page_text, "lxml")
page = new_soup.find("div", class_ = "grap").text
with open("./三国演义.txt", "a", encoding = "utf-8") as fp:
fp.write("\n" + title + ":" + "\n" + "\n" + page)
print(title + "下载完成！！！")
