一个简单的爬虫有问题,希望能达到大家的帮助。

源代码:

import requests
import 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[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=%27 + 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()

运行结果:

序号 价格 商品名称

运行结果并没有报错,但是结果就显示了表头。

你已经做了异常处理, 这里修改一下 ,看看有没有出现啥异常

except:
    continue
except Exception as e:
    print("error",repr(e))
    continue

用插入代码块功能,重新贴一下代码

img