求助各位老哥
import requestsimport re
def getHTMLText(url):
try:
r = requests.get(url,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","商品名称"))
count = 0
for g in ilt:
count = count + 1
print(tplt.format(count,g,g))
print("")
def main():
goods = 'cherry轴键盘'
depth = 2
start_url = 'https://s.taobao.com/search?q=' + goods
infoList = []
for i in range(depth):
try:
url = start_url + '&s='
html = getHTMLText(url)
parsePage(infoList,html)
except:
continue
printGoodsList(infoList)
main()
只打印出了序号,价格和名称三个标题,没有具体的信息,求各位帮我看看哪里出了问题 本帖最后由 疾风怪盗 于 2020-9-16 13:17 编辑
淘宝登陆你是怎么解决的?
print(r.text)
只爬到了登陆前的页面,没有爬到数据
代码里这里也报错了,split前怎么没字符
price = eval(plt, split(':'))
这里也写错了
title = eval(tlt), split(':')
估计不是你自己写的吧,网上抄来的? 要么加cookie试试
要么先用Selenium登陆了之后再获取数据吧
页:
[1]