Python基础之爬虫（持续更新中）

python通过urllib.request.urlopen("https://www.baidu.com")访问网页

实战，去网站上下载一只猫的图片

import urllib.request

response = urllib.request.urlopen('http://placekitten.com/g/500/600')
cat_img = response.read()

with open('cat_500_600', 'wb') as f:
    f.write(cat_img)

或者：

import urllib.request

req = urllib.request.Request('http://placekitten.com/g/500/600')
response = urllib.request.urlopen(req)
cat_img = response.read()

with open('cat_500_600', 'wb') as f:
    f.write(cat_img)

爬虫百度翻译和有道翻译 

直接方法（它们都有反爬虫，所以失败了），f12，可以获得url和from data获得data字典

url='https://fanyi.baidu.com/v2transapi'
data={}
data['from']='en'
data['to']='zh'
data['query']='I love typing code'
data['transtype']='translang'
data['simple_means_flag']=''
data['sign']='94582.365127'
data['token']='ad3ea2606fa89004bad50bbd15aa045b'
data = urllib.parse.urlencode(data).encode('utf-8')

response = urllib.request.urlopen(url, data)
html = response.read().decode('utf-8')

print(html)

通过网上的大神解决了的代码

import urllib.request
import urllib.parse
import json

content = input('请输入要翻译的句子: ')
youdao_url = 'http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule'
baidu_url = 'http://fanyi.baidu.com/basetrans'

data = {}
data2 = {}

data['i']= content
data['from'] = 'AUTO'
data['to'] = 'AUTO'
data['smartresult'] = 'dict'
data['client'] = 'fanyideskweb'
data['salt'] = ''
data['sign'] = '47ee728a4465ef98ac06510bf67f3023'
data['doctype'] = 'json'
data['version'] = '2.1'
data['keyfrom'] = 'fanyi.web'
data['action'] = 'FY_BY_CLICKBUTTION'
data['typoResult'] = 'false'
data = urllib.parse.urlencode(data).encode('utf-8')

data2['from'] = 'zh'
data2['to'] = 'en'
data2['query'] = content
data2['transtype'] = 'translang'
data2['simple_means_flag'] = ''
data2['sign'] = '94582.365127'
data2['token'] = 'ec980ef090b173ebdff2eea5ffd9a778'
data2 = urllib.parse.urlencode(data2).encode('utf-8')

headers = {"User-Agent":"Mozilla/5.0 (Linux; Android 5.1.1; Nexus 6 Build/LYZ28E) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Mobile Safari/537.36"}

youdao_response = urllib.request.urlopen(youdao_url, data)
baidu_re = urllib.request.Request(baidu_url, data2, headers)
baidu_response = urllib.request.urlopen(baidu_re)

youdao_html = youdao_response.read().decode('utf-8')
baidu_html = baidu_response.read().decode('utf-8')

target = json.loads(youdao_html)
target2 = json.loads(baidu_html)

print('【有道】翻译为: %s'%(target['translateResult'][0][0]['tgt']))
print('【百度】翻译为: %s'%(target2['trans'][0]['dst']))