Python通过正则库爬取淘宝商品信息代码实例

# coding:utf-8

import requests
import re

goods = '水杯'
url = 'https://s.taobao.com/search?q=' + goods

r = requests.get(url=url, timeout=10)
html = r.text

tlist = re.findall(r'\"raw_title\"\:\".*?\"', html) # 正则提取商品名称
plist = re.findall(r'\"view_price\"\:\"[\d\.]*\"', html) # 正则提示商品价格

print(tlist)
print(plist)
print(type(plist)) # 正则表达式提取出的商品名称和商品价格都是以列表形式存储数据的

goodlist = []
for i in range(len(tlist)):
  title = eval(tlist[i].split(':')[1]) # eval()函数简单说就是用于去掉字符串的引号
  price = eval(plist[i].split(':')[1])
  goodlist.append([title, price]) # 把每个商品的名称和价格组成一个小列表，然后把所有商品组成的列表追加到一个大列表中
  print(goodlist)

def get_html(url):
  """获取源码html"""
  try:
    r = requests.get(url=url, timeout=10)
    r.encoding = r.apparent_encoding
    return r.text
  except:
    print("获取失败")
def get_data(html, goodlist):
  """使用re库解析商品名称和价格
  tlist:商品名称列表
  plist:商品价格列表"""
  tlist = re.findall(r'\"raw_title\"\:\".*?\"', html)
  plist = re.findall(r'\"view_price\"\:\"[\d\.]*\"', html)
  for i in range(len(tlist)):
    title = eval(tlist[i].split(':')[1]) # eval()函数简单说就是用于去掉字符串的引号
    price = eval(plist[i].split(':')[1])
    goodlist.append([title, price])


def write_data(list, num):
  # with open('E:/Crawler/case/taob2.txt', 'a') as data:
  #  print(list, file=data)
  for i in range(num): # num控制把爬取到的商品写进多少到文本中
    u = list[i]
    with open('E:/Crawler/case/taob.txt', 'a') as data:
      print(u, file=data)


def main():
  goods = '水杯'
  depth = 3  # 定义爬取深度，即翻页处理
  start_url = 'https://s.taobao.com/search?q=' + goods
  infoList = []
  for i in range(depth):
    try:
      url = start_url + '&s=' + str(44 * i) # 因为淘宝显示每页44个商品，第一页i=0,一次递增
      html = get_html(url)
      get_data(html, infoList)
    except:
      continue
  write_data(infoList, len(infoList))
if __name__ == '__main__':
  main()