学了一个多月写个淘宝商品爬虫，是骡子是马也该牵出来溜溜了
自认为最满意的作品，大佬勿喷{:10_327:}有些代码看了可能会觉得啰嗦，技术有限也就这样了{:10_262:}
不足点麻烦大佬们指出来，下次作品争取更上一层楼{:10_275:}
注释部分给小白看的，希望能给你们带来帮助
下面有给大佬们看的没有代码部分
有注释的代码没有注释代码分开放，
爬虫文件
# -*- coding: utf-8 -*-
import scrapy
import json
from Taobao.items import TaobaoItem
# url编码
from urllib.parse import quote
# url解码
from urllib.parse import unquote
class TaobaoSpider(scrapy.Spider):
name = 'taobao'
# allowed_domains = ['taobao.com/']
Quote = input('请输入要搜索的商品名>>>')
pages = input('请输入爬取页数>>>')
start_urls = []
page = 0
ppage = 0
while page <= int(pages): # 判断语句要用int类型
page += 1
if page%2 != 0: # 取奇数
ppage += 1
# 将符合判断语句的url添加到'start_urls'列表 # 翻页规律 # 第一页，第一个异步加载page参数1，ppage参数为1，pageNav参数为true
start_urls.append('https://ai.taobao.com/search/getItem.htm?_tb_token_=353a8b5a1b773&__ajax__=1&pid=mm_10011550_0_0&unid=&clk1=&page={}&pageSize=60&ppage={}&squareFlag=&sourceId=search&ppathName=&supportCod=&city=&ppath=&dc12=&pageNav=true&itemAssurance=&fcatName=&price=&cat=&from=&tmall=&key={}&fcat=&debug=false&maxPageSize=200&sort=&exchange7=&custAssurance=&postFree=&npx=50&location='.format(page,ppage,quote(Quote,'utf-8')))
if page%2 == 0: # 取偶数
# 同上将符合判断的url添加到列表 #第一页，第二个异步加载page参数2，ppage为0，pageNav参数为false
start_urls.append('https://ai.taobao.com/search/getItem.htm?_tb_token_=353a8b5a1b773&__ajax__=1&pid=mm_10011550_0_0&unid=&clk1=&page={}&pageSize=60&squareFlag=&sourceId=search&ppathName=&supportCod=&city=&ppath=&dc12=&pageNav=false&itemAssurance=&fcatName=&price=&cat=&from=&tmall=&key={}&fcat=&ppage=0&debug=false&maxPageSize=200&sort=&exchange7=&custAssurance=&postFree=&npx=50&location='.format(page,quote(Quote,'utf-8')))
print(start_urls)
def parse(self, response):
# 因为在两个js链接中获取数据，（技术有限，数据不会放在同一个文件里）
# 创建第一个csv文件，注意文件编码格式"encoding=utf-8"否则写数据会乱码
f1 = open('{}第一部分.csv'.format(self.Quote), 'w', encoding='utf-8')
f1.write("商品名,价格,店铺网址,图片url\n")
# 创建第二个csv文件
f2 = open('{}第二部分.csv'.format(self.Quote), 'w', encoding='utf-8')
f2.write("商品名,价格,店铺网址,图片url\n")
a = 0
# 链接参数中有"pageNav = false"的链接js数据中没有'p4ptop'数据，它也是要爬取的数据
try:
# 将js解码，并获取所有链接中有'result'下的'auction'内所有信息
auction = json.loads(response.body)['result']['auction']
# 遍历字典'auction'（它里面全是一个一个的列表）
for x in auction:
a += 1
# 将要写入csv文件中的数据信息写成字典
dict2 = {
'name': x['description'], # 商品名
'clickUrl': x['clickUrl'], # 商品价格
'realPrice': x['realPrice'], # 商品url地址
'origPicUrl': x['origPicUrl'],# 商品图片地址
}
print('*'*100)
print(a)
# 数据写入字典中
f1.write("{name},{realPrice},{clickUrl},{origPicUrl}\n".format(**dict2))
item = TaobaoItem()
item['name'] = x['description']
item['clickUrl'] = x['clickUrl']
item['realPrice'] = x['realPrice']
item['origPicUrl'] = x['origPicUrl']
yield item
# 获取所有url中有'result'下的'p4ptop'内所有信息
p4ptop = json.loads(response.body)['result']['p4ptop']
for y in p4ptop:
a += 1
# 同上写入csv文件信息
dict = {
'name': y['title'],
'realPrice': y['salePrice'],
'clickUrl' : y['eurl'],
'origPicUrl' : y['tbGoodSLink'],
}
print('*' * 100)
print(a)
# 同上写入csv文件
f2.write("{name},{realPrice},{clickUrl},{origPicUrl}\n".format(**dict))
item = TaobaoItem()
item['name'] = y['title']
item['clickUrl'] = y['eurl']
item['realPrice'] = y['salePrice']
item['origPicUrl'] = y['tbGoodSLink']
# print('=' * 100)
# print(a)
yield item
# 如果没有'p4ptop'键则跳过，继续执行下面的代码；（注：搜索包含'auction'的代码不能写在错误下，否则不会跳过报错）
# 有的js数据没有'p4ptop'会报KeyError错误，跳过继续
except KeyError:
pass
# 关闭文件
f1.close()
f2.close()
items
# -*- coding: utf-8 -*-
# Define here the models for your scraped items
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/items.html
import scrapy
class TaobaoItem(scrapy.Item):
# 商品名
name = scrapy.Field()
# # 价格
realPrice = scrapy.Field()
# 商品url
clickUrl = scrapy.Field()
# 图片
origPicUrl = scrapy.Field()
管道文件
# -*- coding: utf-8 -*-
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
# 导入处理媒体文件模块
from scrapy.pipelines.images import ImagesPipeline
import scrapy
# 导入同级目录下settings.py代码中设置的下载文件目录
from Taobao.settings import IMAGES_STORE
# 创建文件模块
import os
# 处理媒体文件类
class TaobaoPipeline(ImagesPipeline):
# 下载图片方法，需在管道文件创建'IMAGES_STORE'文件目录
def get_media_requests(self, item, info):
image_link = item['origPicUrl']
# 将图片链接前面加上https并请求链接
yield scrapy.Request('https:'+image_link)
# 重写文件名方法（将下载图片名字改成商品名）
def item_completed(self, results, item, info):
# ==========================================================
# 返回results内容
# print(results)
# [(True,
# {'url': 'https://gaitaobao4.alicdn.com/tfscom/i3/1607379596/O1CN01vv4Zlp2Kl17e4jX7T_!!0-item_pic.jpg',
# 'path': 'full/321e6d31eed0d9fd036968547943219104c6ab4c.jpg',
# 'checksum': 'ca4e396b135ea49bb2a66c4d8806f6fd'}
# )]'
# ==========================================================
# 三元操作；判断'ok'是否为'True'，为真则获取字典内'path'的值
path = for ok, x in results if ok]
# split()分割,提取文件后缀
jpg = for ok, x in results if ok].split('.')[-1]
# 因为商品名有'/'，需要替换掉才能保存文件，要不然会被认为下一级
names = item['name'].replace('/','')
# rename()文件名修改函数；
# 有些图片链接挂了，在'results'里可以看到状态为False;执行时会提示文件保存失败或索引超出范围
# path即文件目录，'path': 'full/321e6d31eed0d9fd036968547943219104c6ab4c.jpg'
# jpg即提取的所有图片格式
os.rename(IMAGES_STORE + path,IMAGES_STORE + names + '.' + jpg)
# 返回
return item
settings.py
BOT_NAME = 'Taobao'
SPIDER_MODULES = ['Taobao.spiders']
NEWSPIDER_MODULE = 'Taobao.spiders'
# 设置图片下载目录
IMAGES_STORE = 'E:/Scrapy/Taobao/Taobao/spiders/img/'
# 设置U-A
USER_AGENT = 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)'
# 管道文件配置
ITEM_PIPELINES = {
'Taobao.pipelines.TaobaoPipeline': 300,
}
没有注释的代码,item、settings两个文件看上面的吧
爬虫文件
# -*- coding: utf-8 -*-
import scrapy
import json
from Taobao.items import TaobaoItem
from urllib.parse import quote
class TaobaoSpider(scrapy.Spider):
name = 'taobao'
Quote = input('请输入要搜索的商品名>>>')
pages = input('请输入爬取页数>>>')
start_urls = []
page = 0
ppage = 0
while page <= int(pages):
page += 1
if page%2 != 0:
ppage += 1
start_urls.append('https://ai.taobao.com/search/getItem.htm?_tb_token_=353a8b5a1b773&__ajax__=1&pid=mm_10011550_0_0&unid=&clk1=&page={}&pageSize=60&ppage={}&squareFlag=&sourceId=search&ppathName=&supportCod=&city=&ppath=&dc12=&pageNav=true&itemAssurance=&fcatName=&price=&cat=&from=&tmall=&key={}&fcat=&debug=false&maxPageSize=200&sort=&exchange7=&custAssurance=&postFree=&npx=50&location='.format(page,ppage,quote(Quote,'utf-8')))
if page%2 == 0:
start_urls.append('https://ai.taobao.com/search/getItem.htm?_tb_token_=353a8b5a1b773&__ajax__=1&pid=mm_10011550_0_0&unid=&clk1=&page={}&pageSize=60&squareFlag=&sourceId=search&ppathName=&supportCod=&city=&ppath=&dc12=&pageNav=false&itemAssurance=&fcatName=&price=&cat=&from=&tmall=&key={}&fcat=&ppage=0&debug=false&maxPageSize=200&sort=&exchange7=&custAssurance=&postFree=&npx=50&location='.format(page,quote(Quote,'utf-8')))
print(start_urls)
def parse(self, response):
f1 = open('{}第一部分.csv'.format(self.Quote), 'w', encoding='utf-8')
f1.write("商品名,价格,店铺网址,图片url\n")
f2 = open('{}第二部分.csv'.format(self.Quote), 'w', encoding='utf-8')
f2.write("商品名,价格,店铺网址,图片url\n")
a = 0
try:
auction = json.loads(response.body)['result']['auction']
for x in auction:
a += 1
dict2 = {
'name': x['description'], # 商品名
'clickUrl': x['clickUrl'], # 商品价格
'realPrice': x['realPrice'], # 商品url地址
'origPicUrl': x['origPicUrl'],# 商品图片地址
}
f1.write("{name},{realPrice},{clickUrl},{origPicUrl}\n".format(**dict2))
item = TaobaoItem()
item['name'] = x['description']
item['clickUrl'] = x['clickUrl']
item['realPrice'] = x['realPrice']
item['origPicUrl'] = x['origPicUrl']
yield item
p4ptop = json.loads(response.body)['result']['p4ptop']
for y in p4ptop:
a += 1
dict = {
'name': y['title'],
'realPrice': y['salePrice'],
'clickUrl' : y['eurl'],
'origPicUrl' : y['tbGoodSLink'],
}
f2.write("{name},{realPrice},{clickUrl},{origPicUrl}\n".format(**dict))
item = TaobaoItem()
item['name'] = y['title']
item['clickUrl'] = y['eurl']
item['realPrice'] = y['salePrice']
item['origPicUrl'] = y['tbGoodSLink']
yield item
except KeyError:
pass
f1.close()
f2.close()
管道文件
# 导入处理媒体文件模块
from scrapy.pipelines.images import ImagesPipeline
import scrapy
from Taobao.settings import IMAGES_STORE
import os
class TaobaoPipeline(ImagesPipeline):
def get_media_requests(self, item, info):
image_link = item['origPicUrl']
yield scrapy.Request('https:'+image_link)
def item_completed(self, results, item, info):
path = for ok, x in results if ok]
jpg = for ok, x in results if ok].split('.')[-1]
names = item['name'].replace('/','')
os.rename(IMAGES_STORE + path,IMAGES_STORE + names + '.' + jpg)
return item
settings.py文件的图片存放目录不能改，要是能改还能把图片分别存放不同文件，有没有大佬能指点一二的（Scrapy框架）
为啥没人看啊 过来顶一下 过来暖下帖，新人还看不懂 淫才啊{:10_254:} 老哥可以的 过来顶一下 学习了
页:
[1]