框架还是一样的
先响应网页,抓取网页文字getHTMLText
然后处理网页找到目标源,这次目标是价格parsePage
最后打印到本地文printGoodsList
import requests
import os
from bs4 import BeautifulSoup
import bs4
import re
def getHTMLText(url):
try:
kv = {'user-agent':'Mozilla/5.0'}
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[i].split(':')[1])
title = eval(tlt[i].split(':')[1])
ilt.append([price,title])
except:
print("")
def printGoodsList(ilt):
path = '你的文件地址.txt'
tplt = "{:4}\t{:8}\t{:16}"
try:
if os.path.exists(path):
with open(path,'wb') as f:
temp = tplt.format('序号','价格','商品名称')+'\r\n'
f.write(temp.encode('utf-8'))
count = 0
for g in ilt:
count = count + 1
temp = tplt.format(count,g[0],g[1])+'\r\n'
f.write(temp.encode('utf-8'))
f.close()
print('done')
except:
print('failed')
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()
注意写地址的时候是//而非\
另外注意转码,OK!