1、未使用模拟浏览器技术
import re
import urllib.request
import urllib.error
url="http://www.79n.cn/bizhi/zhuomian_101/index_2.html"
url1="http://www.79n.cn/bizhi/zhuomian_101/index_"
url2=url1+str(2)+".html"
print(type(url2))
print(url2)
print(url==url2)
try:
html1=urllib.request.urlopen(url1).read()
html1=str(html1)
except urllib.error.HTTPError as e:
print(e.code)
print(e.reason)
print("httperror")
except urllib.error.URLError as e:
print(e.reason)
print("urlerror")
pat='<DIV class=wrapperbizhi>.+?<div style="width:300px;height:500px;" id="mouseOverleft">'
res=re.compile(pat).findall(html1)
pat2="http://(.+?).jpg"
res1=re.compile(pat2).findall(res[0])
<class 'str'>
http://www.79n.cn/bizhi/zhuomian_101/index_2.html
True
404
Not Found
httperror
Traceback (most recent call last):
File "F:/pythonProject/aa.py", line 24, in <module>
res=re.compile(pat).findall(html1)
NameError: name 'html1' is not defined
2、使用模拟浏览器技术
import urllib.error
url="http://www.79n.cn/bizhi/zhuomian_101/index_2.html"
url1="http://www.79n.cn/bizhi/zhuomian_101/index_"
url2=url1+str(2)+".html"
print(type(url2))
print(url2)
print(url==url2)
try:
opener=urllib.request.build_opener()
# 添加opener的请求头(列表形式)
header=("User-Agent",
"Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.76 Mobile Safari/537.36")
opener.addheaders=[header]
# 使用opener的open()方法,访问url
html1=opener.open(url).read()
html1=str(html1)
except urllib.error.HTTPError as e:
print(e.code)
print(e.reason)
print("httperror")
except urllib.error.URLError as e:
print(e.reason)
print("urlerror")
pat='<DIV class=wrapperbizhi>.+?<div style="width:300px;height:500px;" id="mouseOverleft">'
res=re.compile(pat).findall(html1)
pat2="http://(.+?).jpg"
res1=re.compile(pat2).findall(res[0])
print(res1)
<class 'str'>
http://www.79n.cn/bizhi/zhuomian_101/index_2.html
True
['www.79n.cn/uploads/allimg/121102/1-121102094T3']