2426157140 发表于 2020-7-13 17:24:41

萌新淘宝定向爬取商品信息遇到了问题

import requests
import re

def getHTMLText(url):
{"cookie":'',
    "user-agent":"Mozilla/5.0"}
    try:
      r = requests.get(url, headers = kv, timeout = 30)
      r.raise_for_status()
      r.encoding = r.apparent_encoding
      return r.text
    except:
      return ""

def parsePage(ilt, html):
    try:
      plt = re.findall(r'\"view_price\"\:\"[\d\.]*\"', html)
      tlt = re.findall(r'\"raw_title\"\:\".*?\"', html)
      for i in range(len(plt)):
            price = eval(plt.split(':'))
            title = eval(tlt.split(':'))
            ilt.append()
    except:
      print("")

def printGoodsList(ilt):
    tplt = "{:4}\t{:8}\t{:16}"
    print(tplt.format("序号", "价格", "商品名"))
    count = 0
    for g in ilt:
      count = count + 1
      print(tplt.format(count, g, g))

def main():
    goods = '书包'
    depth = 2
    start_url = 'http://s.taobao.com/search?q=' + goods
    infoList = []
    for i in range(depth):
      try:
            url = start_url + '&s=' + str(44*i)
            html = getHTMLText(url)
            parsePage(infoList, html)
      except:
            continue
    printGoodsList(infoList)
   
main()以上是代码cookie我运行时候查了写里面了但是最后运行提示line38：Need type annotation for 'infoList' (hint: "infoList: List[<type>] = ...")

2426157140 发表于 2020-7-13 17:27:51

def getHTMLText(url):
kv = {"cookie":'',
    "user-agent":"Mozilla/5.0"}
    try:
      r = requests.get(url, headers = kv, timeout = 30)
      r.raise_for_status()
      r.encoding = r.apparent_encoding
      return r.text
    except:
      return ""不好意思刚才删cookie时候把kv = {}删了

Twilight6 发表于 2020-7-13 23:32:33


你代码发的有点乱，缩进也不对

import requests
import re


def getHTMLText(url):
    kv = {"cookie":'',
    "user-agent":"Mozilla/5.0"}
    try:
      r = requests.get(url, headers = kv, timeout = 30)
      r.raise_for_status()
      r.encoding = r.apparent_encoding
      return r.text
    except:
      return ""





def parsePage(ilt, html):
    try:
      plt = re.findall(r'"view_price"\:"[\d\.]*"', html)
      tlt = re.findall(r'"raw_title"\:".*?"', html)
      for i in range(len(plt)):
            price = eval(plt.split(':'))
            title = eval(tlt.split(':'))
            ilt.append()
    except:
      print("")


def printGoodsList(ilt):
    tplt = "{:4}\t{:8}\t{:16}"
    print(tplt.format("序号", "价格", "商品名"))
    count = 0
    for g in ilt:
      count = count + 1
      print(tplt.format(count, g, g))


def main():
    goods = '书包'
    depth = 2
    start_url = 'http://s.taobao.com/search?q=' + goods
    infoList = []
    for i in range(depth):
      try:
            url = start_url + '&s=' + str(44 * i)
            html = getHTMLText(url)
            parsePage(infoList, html)
      except:
            continue
    printGoodsList(infoList)


main()
页: [1]
查看完整版本: 萌新淘宝定向爬取商品信息遇到了问题