|
|
import requests
import re
from bs4 import BeautifulSoup
def getHTMLText(url):
user_agent="Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 Safari/537.36 SLBrowser/7.0.0.8031 SLBChan/25"
referer='http://www.google.com/'
kv={'user-Agent':'user_agent','referer':'referer','cookie':'cna=CW/bGZjr0FgCAd9IW5KvPJ5B; sca=2dad4c0f; cad=17c4c20bb64-5123451325930037890001; cap=1ffc; cnaui=2208675988244; aui=2208675988244; tbsa=08631fe094270387e26854f8_1633411912_2; atpsida=f1ee1011d1216aafb727853f_1633411912_2; atpsidas=3a3b699c596572316ec9d24d_1633411912_2'}
r= requests.get(url,headers=kv,timeout=30)
r.raise_for_status()
r.encoding=r.apparent_encoding
return r.text
def parsePage(ilt,html):
print(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(i).split(':')[1])
title=eval(tlt(i).split(':')[1])
ilt.append([price,title])
except:
print("")
def printGoodslist(ilt):
tplt= "{:4}\t{:8}\t{:16}"
print(tplt.format("序号","价格","商品名称"))
count=0
for g in ilt:
count=count+1
print(tplt.format(count,g[0],g[1]))
def main():
goods='书包'
depth=3
start_url='https://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()
为什么我这个代码爬不了任何数据，是代码敲错了吗
|
|
