本文介绍两种爬取方式：
1.正则表达式
2.bs4解析Html
以下为正则表达式爬虫，面向对象封装后的代码如下：
import urllib.request # 用于下载图片
import os
import requests # 发送http请求
import re # 正则表达式匹配 class GetJpg(object): def __init__(self, start_urls):
self.start_urls = start_urls def get_response(self,url): '''获取网页响应内容''' response = requests.get(url).text
return response def get_content(self,html): '''获取网页响应内容中所有图片的整体div部分''' reg = re.compile(r'(<div class="j-r-list-c">.*?</div>.*?</div>)', re.S)
return re.findall(reg, html) def get_jpg_url(self,content): '''获取图片url''' reg = r'data-original="(.*?)"'
return re.findall(reg, content) def get_jpg_name(self,content): ''' 获取图片名称''' reg = re.compile(r'<a href="/detail-.{8}.html">(.*?)</a>')
return re.findall(reg, content) def download_jpg(self,src_url, path,index): '''下载图片保存到本地目录''' path = ''.join(path.split())
path = 'E:\Python\爬图片\{name}.{index}'.format(name=path,index=index)
if not os.path.exists(path):
urllib.request.urlretrieve(src_url, path) # 下载图片
print('OK!!!')
else:
print('文件已存在') def get_url_name(self,start_url): ''' 逐页下载,本部分本来可以放在main函数里，考虑到会多嵌套一个循环所以单独拿出来作为一个函数''' content = self.get_content(self.get_response(start_url))
for i in content:
jpg_url = self.get_jpg_url(i)
if jpg_url:
jpg_name = self.get_jpg_name(i)
index = jpg_url[0].split('.')[-1]
try:
self.download_jpg(jpg_url[0], jpg_name[0],index)
except:
continue def main(self): ''' 执行''' [self.get_url_name(start_url) for start_url in self.start_urls] # 此处列表生成器来执行
# 这部分的代码相当于：
# for start_url in self.start_urls:
# self.get_url_name(start_url) if __name__ == '__main__':
start_urls = ['http://www.budejie.com/{id}'.format(id=i) for i in range(1,10)]
jpg = GetJpg(start_urls) # 实例化一个对象
jpg.main()
以下为使用bs4爬取的代码：
from bs4 import BeautifulSoup
import urllib.request
import re def get_urls(img_girl):
'''
:param img_girl: <img>标签内容
:return: 所有图片的url
'''
all_urls = [girl.get('src') for girl in img_girl]
return all_urls def get_img_name(img_girl):
'''
:param img_girl: <img>标签内容
:return: 所有图片title
''' all_name = [girl.get('title') for girl in img_girl]
return all_name def get_img_resource(url):
'''
:param url:网站url
:return:网页源码中的所有<img>标签内容
'''
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.78 Safari/537.36',
'Accept - Language': 'zh - CN, zh;q = 0.8'
} # 添加请求头部，模拟浏览器
req = urllib.request.Request(url, headers=headers) # 创建对象
res = urllib.request.urlopen(req, timeout=20) # 发送请求
content = res.read() # 获取响应网页源码
soup = BeautifulSoup(content,'html.parser') # HMTL源码解析
img_girl = soup.find_all('img') # 获取 源码中的<img>标签模块内容
return img_girl def main(url):
'''
下载保存图片
:param url: 网站url
'''
urls = get_urls(get_img_resource(url))
names = get_img_name(get_img_resource(url))
x = 1
for src_url in urls:
path_l = re.split(r'\W', names[urls.index(src_url)]) # 去除图片名称中的特殊字符,不然文件名可能在保存的时候报错
path = ''.join(path_l)
path = 'E:\Python\爬图片\BS4\{name}_{index}.jpg'.format(name=path,index=x)
urllib.request.urlretrieve(src_url, path)
print('OK')
x += 1 if __name__ == "__main__":
urls = ['https://www.dbmeinv.com/dbgroup/show.htm?cid=4&pager_offset={i}'.format(i=id)for id in range(1,10) ]
[main(url)for url in urls]
bs4面向对象封装后代码：
from bs4 import BeautifulSoup
import urllib.request
import re class GetWebImg(object): def __init__(self, url, index):
self.url = url
self.index = index def get_urls(self,img_girl):
'''
:param img_girl: <img>标签内容
:return: 所有图片的url
'''
all_urls = [girl.get('src') for girl in img_girl]
return all_urls def get_img_name(self,img_girl):
'''
:param img_girl: <img>标签内容
:return: 所有图片title
''' all_name = [girl.get('title') for girl in img_girl]
return all_name def get_img_resource(self, url):
'''
:param url:网站url
:return:网页源码中的所有<img>标签内容
'''
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.78 Safari/537.36',
'Accept - Language': 'zh - CN, zh;q = 0.8'
} # 添加请求头部，模拟浏览器
req = urllib.request.Request(url, headers=headers) # 创建对象
res = urllib.request.urlopen(req, timeout=20) # 发送请求
content = res.read() # 获取响应网页源码
soup = BeautifulSoup(content, 'html.parser') # HMTL源码解析
img_girl = soup.find_all('img') # 获取 源码中的<img>标签模块内容
return img_girl def main(self):
'''
下载保存图片
:param url: 网站url
'''
url_list = self.get_urls(self.get_img_resource(self.url))
name_list = self.get_img_name(self.get_img_resource(self.url))
x = 1
for src_url in url_list:
path_l = re.split(r'\W', name_list[url_list.index(src_url)]) # 去除图片名称中的特殊字符,不然文件名可能在保存的时候报错
path = ''.join(path_l)
path = 'E:\Python\爬图片\BS4\{name}_{index}_{id}.jpg'.format(name=path, index=self.index,id =x)
urllib.request.urlretrieve(src_url, path)
print('第{index}页第{id}张图片下载OK'.format(index=self.index,id =x))
x += 1 if __name__ == "__main__":
urls = ['https://www.dbmeinv.com/dbgroup/show.htm?cid=4&pager_offset={i}'.format(i=id)for id in range(1,10) ]
index = 1
for url in urls:
get_img = GetWebImg(url,index)
get_img.main()
index += 1
运行结果：