Python之网络爬虫

例1：下载网页中的图片（必须在运行代码前打开网页,如http://placekitten.com/g/300/200）：

import urllib.request

response = urllib.request.urlopen("http://placekitten.com/g/300/200")
cat_img = response.read()
with open('cat_300_200.jpg','wb') as f:
    f.write(cat_img)

例2：利用有道翻译进行英汉互译：右键网页选择审查元素->将Request URL的地址写入url->将From Data下的列表写入data字典->encode编码，decode译码，json将字符串转换为字典。

import urllib.request
import urllib.parse
import json

str = input("请输入要翻译的内容")#在这里输入想要翻译的内容
url = "http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule&sessionFrom="
data = {}
data['i'] = str
data['from'] = 'AUTO'
data['to'] = 'AUTO'
data['smartresult']  = 'dict'
data['client'] = 'fanyideskweb'
data['salt'] = '15634369131520'
data['sign'] = '172ab59aa2b0aa54c4bf49dece623a75'
data['ts'] = '1563436913152'
data['bv'] = 'f355c521b6e13c15aa35c72a097b7786'
data['doctype'] = 'json'
data['version'] = '2.1'
data['keyfrom'] = 'fanyi.web'
data['action'] = 'FY_BY_REALTlME'

data = urllib.parse.urlencode(data).encode('utf-8')
response = urllib.request.urlopen(url,data)
ret = response.read().decode('utf-8')
#print(ret)
target = json.loads(ret)
# print(target)
# print(target['translateResult'])
# print(target['translateResult'][0])
# print(target['translateResult'][0][0])
# print(target['translateResult'][0][0]['src'])
# print(target['translateResult'][0][0]['tgt'])
print("%s 的翻译结果是 %s" %(target['translateResult'][0][0]['src'],target['translateResult'][0][0]['tgt']))
>>>请输入要翻译的内容我是帅哥
>>>我是帅哥 的翻译结果是 I am a handsome boy