源码:
#!/usr/bin/env python
# -*- encoding: utf-8 -*-
# Created on 2016-03-29 10:59:36
# Project: taonvlang
from pyspider.libs.base_handler import *
DIR_PATH = 'E:/taonvlang'
class Handler(BaseHandler):
crawl_config = {
}
def __init__(self):
self.base_url = 'https://mm.taobao.com/json/request_top_list.htm?page='
self.pages= 10
self.deal = Deal()
@every(minutes=24 * 60)
def on_start(self):
#爬取多页
for ipage in range(1, self.pages):
url = self.base_url + str(ipage)
print url
self.crawl(url, callback=self.index_page, validate_cert=False)
@config(age=10 * 24 * 60 * 60)
def index_page(self, response):
for each in response.doc('.lady-avatar').items():
self.crawl(each.attr.href, callback=self.detail_page, validate_cert=False)
@config(priority=2)
def detail_page(self, response):
name = response.doc('.mm-p-model-info-left-top dd > a').text()
dir_path = self.deal.mkDir(name)
#先抓大再抓小
brief = response.doc('.mm-aixiu-content').text()
imgs = response.doc('.mm-aixiu-content img').items()
count = 1
self.deal.saveBrief(brief, dir_path, name)
for img in imgs:
url = img.attr.src
if url:
print url
count += 1
extension = self.deal.getExtension(url)
file_name = name + str(count) + '.' + extension
self.crawl(img.attr.src, callback=self.save_img, save={'dir_path': dir_path, 'file_name': file_name}, validate_cert=False)
return {
"name":name,
"url": response.url,
"title": response.doc('title').text(),
}
#抓到图片后保存
def save_img(self, response):
content = response.content
dir_path = response.save['dir_path']
file_name = response.save['file_name']
file_path = dir_path + '/' + file_name
self.deal.saveImg(content, file_path)
import os
class Deal:
def __init__(self):
self.path = DIR_PATH
if not self.path.endswith('/'):
self.path = self.path + '/'
if not os.path.exists(self.path):
os.makedirs(self.path)
def mkDir(self, path):
path = path.strip()
dir_path = self.path + path
exists = os.path.exists(dir_path)
if not exists:
os.makedirs(dir_path)
return dir_path
else:
return dir_path
def saveImg(self, content, path):
f = open(path, 'wb')
f.write(content)
f.close()
def saveBrief(self, content, dir_path, name):
file_name = dir_path + "/" + name + ".txt"
f = open(file_name, "w+")
f.write(content.encode('utf-8'))
def getExtension(self, url):
extension = url.split('.')[-1]
return extension
源码参考:http://cuiqingcai.com/2652.html
相比原来源码优化了一个步骤,因此更简单点。