urllib是 由 python3 提供一系列操作url的库,模拟用户使用浏览器访问网页。
Beautiful Soup 是 python 用于处理抓取的网页数据的一个库。
1.前提条件
搭建 python 环境
安装 pycharm
安装 pymysql:pip install pymysql
2.导入 urllib
2.1 打开pycharm,新建 py 文件,抓取百度首页内容
# 导入urllib包
from urllib import request
# 输入url
resp = request.urlopen('http://www.baidu.com/')
# 输出响应数据,read().decode()解析编码
print(resp.read().decode('utf-8'))
运行如下:
2.2 如需携带头部文件,如 Origin、User-Agent,使用 resp.add_header(key,value)方法。
# 导入urllib包
from urllib import request
# 新建url
resp = request.Request('http://www.baidu.com/')
# 添加头部文件
resp.add_header("User-Agent","Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36")
# 输入url
rep = request.urlopen(resp)
# 输出响应数据,read().decode()解析编码
print(rep.read().decode('utf-8'))
2.3 使用 post 请求
postData = parse.urlencode({
(key,value),
(key,value),
...
})
rep = request.urlopen(resp,data=postData.encode('utf-8'))
3.安装 Beautiful Soup
查看 Beautiful Soup4 文档
下载 Beautiful Soup4
或者 pip install beautifulsoup4
安装
3.1 解析一段 html 文本
# 导入BeautifulSoup包
from bs4 import BeautifulSoup as bs
# 新建html文本
doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title"><b>The Dormouse's story</b></p>
<p class="story">Once upon a time there were three little sisters; and their names were
<a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>,
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
<a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
and they lived at the bottom of a well.</p>
<p class="story">...</p>
"""
# 解析doc
soup = bs(doc,"html.parser")
# 输出soup,prettify()按照标准缩进格式
print(soup.prettify())
输出结果
3.2 抓取数据的方法
soup.title
# <title>The Dormouse's story</title>
soup.title.name
# 'title'
soup.title.string
# 'The Dormouse's story'
# 识别一个
soup.get_text()
# The Dormouse's story
#
# The Dormouse's story
#
# Once upon a time there were three little sisters; and their names were
# Elsie,
# Lacie and
# Tillie;
# and they lived at the bottom of a well.
#
# ...
# 识别多个
soup.title.parent.name
# 'head'
soup.p
# <p class="title"><b>The Dormouse's story</b></p>
soup.p['class']
# ['title']
soup.a
# <a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>
soup.find_all('a')
# [<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>,
# <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>,
# <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]
soup.find_all("a",href=re.compile(r"^http://example\.com/e"))
# [<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>]
# re.compile 正则表达式,需 import re
soup.find(id="link3")
# <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>
soup.find("p",{"class":"story"})
# <p class="story">Once upon a time there were three little sisters; and their names were
# <a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>,
# <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a> and
# <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>;
# and they lived at the bottom of a well.</p>
for link in soup.find_all('a'):
print(link.get('href'))
# http://example.com/elsie
# http://example.com/lacie
# http://example.com/tillie
3.3 解析网页 html,获取中国知网上的各行业服务链接
# 导入包
from urllib import request
from bs4 import BeautifulSoup as bs
import re
# 新建url
rep = request.Request('https://www.cnki.net/')
# 添加头部
rep.add_header("User-Agent","Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36")
# 获取网页数据
resp = request.urlopen(rep).read().decode('utf-8')
# 使用 Beautiful Soup解析网页
soup = bs(resp,"html.parser")
# print(soup)
# 获取所有链接含有/r.cnki.net/的a标签
lists = soup.find_all("a",href=re.compile("/r.cnki.net/"))
# print(lists)
# 循环列出所有url
for url in lists:
# if not re.search("\.(jpg|JPG)$",url["href"]):
print(url.get_text(),"------","https:" + url['href'])
输出结果
4.持久化数据
4.1 新建一张表 cnki,字段 id,name,url(id为主键,且设为自增长)
4.2 将数据存储到 cnki 表
# 导入包
from urllib import request
from bs4 import BeautifulSoup as bs
import re
# 导入pymysql
import pymysql
# 新建url
rep = request.Request('https://www.cnki.net/')
# 添加头部
rep.add_header("User-Agent","Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36")
# 获取网页数据
resp = request.urlopen(rep).read().decode('utf-8')
# 使用 Beautiful Soup解析网页
soup = bs(resp,"html.parser")
# print(soup)
# 获取所有链接含有/r.cnki.net/的a标签
lists = soup.find_all("a",href=re.compile("/r.cnki.net/"))
# print(lists)
# 循环列出所有url
for url in lists:
# if not re.search("\.(jpg|JPG)$",url["href"]):
print(url.get_text(),"------","https:" + url['href'])
# 连接数据库
conn = pymysql.connect(host = "localhost",port = 3306,
user = 'root',passwd = "123456",
db = 'py_fecth',charset = 'utf8')
# 跳过异常,直接关闭数据库
try:
# with conn.cursor() as data:
# 定义会话指针
data = conn.cursor()
# 定义sql语句
sql = "insert into `cnki` (`name`,`url`) values (%s,%s)"
# 执行sql语句
data.execute(sql,(url.get_text(),"https:" + url['href']))
# 提交数据
conn.commit()
# 关闭会话指针
data.close()
finally:
# 关闭数据库
conn.close()
4.3 cnki 表引入39条数据
4.4 查询数据库
# 导入pymysql
import pymysql
# 连接数据库
conn = pymysql.connect(host = "localhost",port = 3306,
user = 'root',passwd = "123456",
db = 'py_fecth',charset = 'utf8')
# 跳过异常,直接关闭数据库
try:
# with conn.cursor() as data:
# 定义会话指针
data = conn.cursor()
# 定义sql语句
sql = "select `name`,`url` from `cnki` where `id` is not null"
# 统计总记录数
count = data.execute(sql)
print(count)
# 查询几行数据
res = data.fetchmany(size=1)
print(res)
# 查询下一行
print(data.fetchone())
# 获取所有数据
result = data.fetchall()
# for i in result:
# print(i)
# 关闭会话指针
data.close()
finally:
# 关闭数据库
conn.close()
输出结果