最基础网页爬虫

Posted 2020-09-21 激动的阿涛

第一个网页文本爬虫程序（没有添加下载器）：

 1 import requests
 2 from bs4 import BeautifulSoup
 3 import os
 4 
 5 headers={‘User-Agent‘:"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (Khtml,like Gecko) Chrome/22.0.1207.1 Safari/537.1"}
 6 url_begin= ‘http://www.liaoxuefeng.com/wiki/0014316089557264a6b348958f449949df42a6d3a2e542c000‘
 7 start_url=requests.get(url_begin,headers=headers)
 8 #print(start_url.text)
 9 Soup=BeautifulSoup(start_url.text,‘lxml‘)
10 link_list=Soup.find(‘div‘,class_="x-sidebar-left-content").find_all(‘a‘)
11 #print(link_list)
12 
13 for link in link_list:
14         url=‘http://www.liaoxuefeng.com‘ + link[‘href‘]
15         html=requests.get(url,headers=headers)
16         html_Soup=BeautifulSoup(html.text,‘lxml‘)
17         title_list = html_Soup.find(‘div‘, class_="x-content").find_all(‘h4‘)
18         # print(title_list)
19         for title in title_list:
20             titlereal = title.get_text()
21             print(titlereal)
22 
23         content_list = html_Soup.find("div", class_="x-wiki-content").find_all(‘p‘)
24         for content in content_list:
25             # print(content)
26             contentreal = content.get_text()
27             print(contentreal)

 

 

 

 

第二个网页图片爬虫（引入os模块，可以将网页内容爬取到本地文件夹）

 1 import requests
 2 from bs4 import BeautifulSoup
 3 import os
 4 import urllib
 5 import urllib3
 6 
 7 url= ‘http://www.dbmeinv.com/?pager_oofset=1‘
 8 x=0
 9 
10 def crawl(url):
11     headers = {
12         ‘User-Agent‘: "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTMl,like Gecko) Chrome/22.0.1207.1 Safari/537.1"}
13     req=requests.get(url,headers=headers)
14 
15     Soup=BeautifulSoup(req.text,‘lxml‘)
16     link_list=Soup.find_all(‘img‘)
17     for girl in link_list:
18         link= girl.get(‘src‘)
19         print(link)
20 
21         global x
22         path=r‘/Users/wangxitao/Desktop/douban‘
23         local=os.path.join(path,‘image\%s.jpg‘%x)
24         urllib.request.urlretrieve(link,local)
25                                          #‘image\%s.jpg‘%x
26 
27         x+=1
28         print("正在下载第%s张"%x)
29 
30 for page in range(1,10):
31     page+=1
32     url=‘http://www.dbmeinv.com/?pager_offset=%d‘%page
33     crawl(url)
34 
35 print(‘爬取完毕‘)