【python】爬取京东华硕笔记本自营店代码

配合视频使用（空间里有，还没过审核就没链接）

import urllib.request

from bs4 import BeautifulSoup

import re

import pandas

import time

time.sleep(2)

import json

url_txt = open('C:/Users/28051/Desktop/pclinks.txt','r',encoding='utf-8')   #写入的文件

url = url_txt.read().split('\n')

url.pop(99)

print(len(url))

pat = 'http://item.jd.com/(.*?).html'

id = re.compile(pat).findall(str(url))

print(len(id))

headers = ('User-Agent',

          'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36')

pc_info = []

for url_i in url:

   print(url_i)

   html = urllib.request.urlopen(url_i)

   soup = BeautifulSoup(html,'lxml')

   data = soup.find_all('ul',{'class':'parameter2 p-parameter-list'})

   for item in data:

       result = item.get_text()

       result.lstrip()

       result.rstrip()

   pc_info.append(result)

   print(len(pc_info))

pp = []

pm = []

pop = []

commentcount = []

goodrate = []

for price_i in id:

   pc_price_url = 'https://p.3.cn/prices/mgets?skuIds=J_' + price_i

   pc_json = json.load(urllib.request.urlopen(pc_price_url, timeout=5))[0]

   pc_price_p_data = pc_json['p']  # 现在的价格

   pc_price_m_data = pc_json['m']  # 最高价

   pc_price_op_data = pc_json['op']  # 指导价

   pp.append(pc_price_p_data)

   pm.append(pc_price_m_data)

   pop.append(pc_price_op_data)

   pc_count_url = 'https://club.jd.com/comment/skuProductPageComments.action?callback=fetchJSON_comment98&productId='+price_i+'&score=0&sortType=5&page=0&pageSize=10&isShadowSku=0&fold=1'

   pc_count_html = urllib.request.urlopen(pc_count_url).read().decode('GBK')

   pc_count_html1 = pc_count_html.replace('fetchJSON_comment98(', '')

   pc_count_html2 = pc_count_html1.replace(');', '')

   pc_count_js = json.loads(pc_count_html2)

   pc_count_data = pc_count_js['productCommentSummary']

   commentCount = pc_count_data['commentCount']

   goodRate = pc_count_data['goodRate']

   commentcount.append(commentCount)

   goodrate.append(goodRate)

   '''generalCount = pc_count_data['generalCount']

   generalRate = pc_count_data['generalRate']

   poorCount = pc_count_data['poorCount']

   videoCount = pc_count_data['videoCount']

   showCount = pc_count_data['showCount']'''

   print(len(pp))

   print(len(pm))

   print(len(pop))

   print(len(commentcount))

   print(len(goodrate))

pc_data = {'url':url,'id':id,'info':pc_info,'pp':pp,'pm':pm,'pop':pop,'commentcount':commentcount,'goodrate':goodrate}

frame = pandas.DataFrame(pc_data)

frame.to_csv('C:/Users/28051/Desktop/pc.csv',encoding='utf-8-sig')

print(frame)