python爬虫实现获取下一页代码

(编辑：jimmy 日期: 2024/11/19 浏览：3 次 )

我们首先来看下实例代码：

from time import sleep

import faker
import requests
from lxml import etree

fake = faker.Faker()

base_url = "http://angelimg.spbeen.com"

def get_next_link(url):
  content = downloadHtml(url)
  html = etree.HTML(content)
  next_url = html.xpath("//a[@class='ch next']/@href")
  if next_url:
    return base_url + next_url[0]
  else:
    return False

def downloadHtml(ur):
  user_agent = fake.user_agent()
  headers = {'User-Agent': user_agent,"Referer":"http://angelimg.spbeen.com/"}
  response = requests.get(url, headers=headers)
  return response.text

def getImgUrl(content):
  html = etree.HTML(content)
  img_url = html.xpath('//*[@id="content"]/a/img/@src')
  title = html.xpath(".//div['@class=article']/h2/text()")

  return img_url[0],title[0]

def saveImg(title,img_url):
  if img_url is not None and title is not None:
    with open("txt/"+str(title)+".jpg",'wb') as f:
      user_agent = fake.user_agent()
      headers = {'User-Agent': user_agent,"Referer":"http://angelimg.spbeen.com/"}
      content = requests.get(img_url, headers=headers)
      #request_view(content)
      f.write(content.content)
      f.close()

def request_view(response):
  import webbrowser
  request_url = response.url
  base_url = '<head><base href="%s" rel="external nofollow" >' %(request_url)
  base_url = base_url.encode()
  content = response.content.replace(b"<head>",base_url)
  tem_html = open('tmp.html','wb')
  tem_html.write(content)
  tem_html.close()
  webbrowser.open_new_tab('tmp.html')

def crawl_img(url):
  content = downloadHtml(url)
  res = getImgUrl(content)
  title = res[1]
  img_url = res[0]
  saveImg(title,img_url)

if __name__ == "__main__":
  url = "http://angelimg.spbeen.com/ang/4968/1"

  while url:
    print(url)
    crawl_img(url)
    url = get_next_link(url)

python 爬虫如何执行自动下一页循环加载文字

from bs4 import BeautifulSoup
import requests
import time
from lxml import etree
import os
# 该demo执行的为如何利用bs去爬一些文字
def start():
  # 发起网络请求
  html=requests.get('http://www.baidu.com')
  #编码
  html.encoding=html.apparent_encoding
  #创建sp
  soup=BeautifulSoup(html.text,'html.parser')
  print(type(soup))
  print('打印元素')
  print(soup.prettify())
  #存储一下title 该方法没有提示直接展示
  title=soup.head.title.string
  print(title)
#   写入文本
  with open(r'C:/Users/a/Desktop/a.txt','w') as f:
    f.write(title)
  print(time.localtime())
 
url_2 = 'http://news.gdzjdaily.com.cn/zjxw/politics/sz_4.shtml'
def get_html_from_bs4(url):
 
  # response = requests.get(url,headers=data,proxies=ip).content.decode('utf-8')
  response = requests.get(url).content.decode('utf-8')
  soup = BeautifulSoup(response, 'html.parser')
  next_page = soup.select('#displaypagenum a:nth-of-type(9)')[0].get('href')
  # for i in nett
  print(next_page)
  next2='http://news.gdzjdaily.com.cn/zjxw/politics/'+next_page
 
 
def get_html_from_etree(url):
 
  response = requests.get(url).content.decode('utf-8')
  html= etree.HTML(response)
 
  next_page = html.xpath('.//a[@class="PageNum"][8]/@href')[0]
  print(next_page)
  # next2='http://news.gdzjdaily.com.cn/zjxw/politics/'+next_page
 
 
get_html_from_etree(url_2)
 
if __name__ == '__main__':
  start()

上一篇：django model object序列化实例
下一篇：浅析python标准库中的glob