import?urllib.request
import?re
user_agent?=?'Mozilla/4.0?(compatible;?MSIE?5.5;?Windows?NT)'
headers?=?{?'User-Agent'?:?user_agent?}
url='http://waimai.baidu.com/waimai/shoplist/7ff6ee1800f46e66'
request=urllib.request.Request(url,headers=headers)
response=urllib.request.urlopen(request)
pagecode=response.read().decode('utf-8')
pattern=re.compile('<li?class="list-item?shopcard?data.*?<div?class="title"?title=(.*?)</div>')
items=re.findall(pattern,pagecode)
for?item?in?items:
????print(item[0])目的是爬取外賣商家的名稱，url在代碼里了不知道為什么爬取不到任何信息求解
python爬蟲的問題
Leo_clip
2017-08-16 09:33:38
