【Python爬虫基础】抓取知乎页面所有图片

 

抓取地址所有图片

#! /usr/bin/env python
from urlparse import urlsplit
from os.path import basename
import urllib2
import re
import requests
import os
import json


url = 'https://www.zhihu.com/question/37787176'

if not os.path.exists('images'):
    os.mkdir("images")

print("start>>>>>>>")

page_size = 50
offset = 0
url_content = urllib2.urlopen(url).read()
answers = re.findall('h3 data-num="(.*?)"', url_content)
limits = int(answers[0])

while offset < limits:
    post_url = "http://www.zhihu.com/node/QuestionAnswerListV2"
    params = json.dumps({
        'url_token': 37787176,
        'pagesize': page_size,
        'offset': offset
    })
    data = {
        '_xsrf': '',
        'method': 'next',
        'params': params
    }
    header = {
        'User-Agent': "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:34.0) Gecko/20100101 Firefox/34.0",
        'Host': "www.zhihu.com",
        'Referer': url
    }
    response = requests.post(post_url, data=data, headers=header)
    answer_list = response.json()["msg"]
    img_urls = re.findall('img .*?src="(.*?_b.*?)"', ''.join(answer_list))
    for img_url in img_urls:
        try:
            img_data = urllib2.urlopen(img_url).read()
            file_name = basename(urlsplit(img_url)[2])
            print(file_name)
            output = open('images/' + file_name, 'wb')
            output.write(img_data)
            output.close()
        except:
            pass
    offset += page_size

print("end>>>>>>>")

正则抓取网页title

#!/usr/bin/python  
# coding:utf-8   
import httplib2  
import urllib2  
import re #正则表达式模块  

class PageClass:  
    #获取指定url的网页内容  
    def get_page(self,url,headers):  
        http=httplib2.Http()  
        response,content=http.request(url,'GET',headers=headers)
        return content.decode('utf-8')

def main():              
    headers={"cookie":'your cookie'}
    url = 'http://v.ktgj.com'
    #print headers
    page = PageClass()
    content = page.get_page(url,headers)
    return content

if __name__ == "__main__":
    htmltext = main()
    pattern = re.compile(r'<title>(.*?)</title>')
    match = pattern.match(htmltext)
    if match:
        print match.group()
    print htmltext

下载网页图片

#! /usr/bin/env python
from urlparse import urlsplit
from os.path import basename
import urllib2
import re
import requests
import os
import json
import datetime

if not os.path.exists('images'):
    os.mkdir("images")

print("start>>>>>>>>>>>>>>>>>>>>>>>")

url = "http://www.ssff66.com/se/jingpintaotu/519271.html"
response = requests.get(url)
#print(response.text)
img_urls = re.findall('img .*?src="(.*?)"', response.text)
#print(img_urls)

for img_url in img_urls:
    try:
        img_data = urllib2.urlopen(img_url,timeout = 5).read()
        file_name = basename(urlsplit(img_url)[2])
        print(datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S') + "  " + file_name)
        output = open('images/' + file_name, 'wb')
        output.write(img_data)
        output.close()
    except Exception,e:
        print("error : " + e.message)
        pass

print("end>>>>>>>>>>>>>>>>>>>>>>>")