2020-02-16

#python爬虫## 爬虫框架
import requests
import re
def getHTMLText(url)
tyr:
r=requests,get(url,timeout=30)
r.raise_for_status()
r.encoding=‘utf-8’
return r.text
except:
return " "
def parserPage(item,html):
try:
plt = re.search(r’“confirmed”:"[\d.]"’,html)
for i in range(len(plt)):
price=eval(plt[i].split(’:’)[1])
item.append(print)
except:
print(’’)
def printGoodList(item):
tplie = “{:4}\t{:8}\t{:16}”
print(tplie.format(’’,’’,’’)
cout = 0
for get in it :
cout = =cout +1
print (tplt.format(cout,g[0],g[1])
print (’’)
def main()
godds=
depaht=2
star_ulr=" "
infoList = []
for i in range (depath):
try:
url=star_url +’&s=’ + str(441)
html = getHTMLText(url)
parserPage(infoList,html)
except:
continue
printGoodList(infoList)
main()