微信 答题王 +百度文字识别 + 百度搜索
pa_baidu(主程序) 精细化写法
# -*- coding: utf-8 -*-
# 斌彬电脑
# @Time : 2018/10/14 0014 18:49
import requests
from lxml import etree
import word_recognition # 文字识别
def get_baidu(n):
data = {
\'ie\': \'utf-8\',
\'f\': \'8\',
\'rsv_bp\': \'1\',
\'tn\': \'baidu\',
\'wd\': n,
# oq: %E7%99%BE%E5%BA%A6AI
# rsv_pq: bcd001050002f85f
# rsv_t: 917dLv7wOh1bo2MqUOyxMbUfkHk+wKfsn40nNpF801PthDw64QzEHZduOg4
\'rqlang\': \'cn\',
\'rsv_enter\': \'1\',
\'rsv_sug3\': \'2\',
\'rsv_sug1\': \'2\',
\'rsv_sug7\': \'100\',
\'rsv_n\': \'2\',
\'rsv_sug2\': \'0\',
# inputT: \'748\'
# rsv_sug4: 1520
}
# url = \'https://www.baidu.com/s?ie=utf-8&f=8&rsv_bp=1&tn=baidu&wd=%E5%B9%BF%E6%92%AD%E7%94%B5%E5%8F%B0&oq=%25E7%2599%25BE%25E5%25BA%25A6AI&rsv_pq=bcd001050002f85f&rsv_t=917dLv7wOh1bo2MqUOyxMbUfkHk%2BwKfsn40nNpF801PthDw64QzEHZduOg4&rqlang=cn&rsv_enter=1&rsv_sug3=2&rsv_sug1=2&rsv_sug7=100&rsv_n=2&rsv_sug2=0&inputT=748&rsv_sug4=1520\'
url = \'https://www.baidu.com/s\'
h2 = {
\'User-Agent\': \'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.81 Safari/537.36\'
}
res = requests.get(url, data, headers=h2)
# print(res.text)
html = etree.HTML(res.text)
# 百度搜索结果的每个连接装在列表中
ht = html.xpath(\'//h3[@class="t"]/*/@href\')
# print(ht)
li = []
for i in ht:
res_ = requests.get(i, headers=h2)
re = etree.HTML(res_.content)
p = re.xpath(\'//*/text()\')
# p = re.xpath(\'//meta/@content\')
li.append(\'\'.join(p))
return li
if __name__ == \'__main__\':
b = word_recognition.BaiDuAPI(\'co.ini\')
# 文字误国后得到列表
text = b.shi_bie(\'1.png\')
# 将列表里的元素的长度放入 l 的列表
l = []
for i in text:
l.append(len(i))
# print(l)
# 找出最长的元素
x = 0
for i in range(len(l)):
if i + 1 != len(l):
if l[i] > x:
x = l[i]
else:
x = x
# 通过这个下标找到题目
tx = text[l.index(x)]
try:
print(\'题目是：\', tx)
print(\'正在百度搜索答案......\')
# 百度搜索得到列表 a
a = get_baidu(tx)
# 把列表拼接成字符串
a = \'\'.join(a)
# print(a)
if text[l.index(x) + 1] in a:
print(\'答案是：1 \', text[l.index(x) + 1])
elif text[l.index(x) + 2] in a:
print(\'答案是：2 \', text[l.index(x) + 2])
elif text[l.index(x) + 3] in a:
print(\'答案是：3 \', text[l.index(x) + 3])
elif text[l.index(x) + 4] in a:
print(\'答案是： 4 \', text[l.index(x) + 4])
# print(\'\'.join(a))
except Exception as e:
print(\'找不到\')
pa_baidu(主程序)
# -*- coding:utf-8 -*-
# 斌彬电脑
# @Time : 2018/9/9 0009 下午 1:17
import requests
from lxml import etree
import word_recognition # 文字识别
def get_baidu(n):
data = {
\'ie\': \'utf-8\',
\'f\': \'8\',
\'rsv_bp\': \'1\',
\'tn\': \'baidu\',
\'wd\':n,
# oq: %E7%99%BE%E5%BA%A6AI
# rsv_pq: bcd001050002f85f
# rsv_t: 917dLv7wOh1bo2MqUOyxMbUfkHk+wKfsn40nNpF801PthDw64QzEHZduOg4
\'rqlang\': \'cn\',
\'rsv_enter\':\'1\',
\'rsv_sug3\': \'2\',
\'rsv_sug1\': \'2\',
\'rsv_sug7\': \'100\',
\'rsv_n\': \'2\',
\'rsv_sug2\': \'0\',
# inputT: \'748\'
# rsv_sug4: 1520
}
# url = \'https://www.baidu.com/s?ie=utf-8&f=8&rsv_bp=1&tn=baidu&wd=%E5%B9%BF%E6%92%AD%E7%94%B5%E5%8F%B0&oq=%25E7%2599%25BE%25E5%25BA%25A6AI&rsv_pq=bcd001050002f85f&rsv_t=917dLv7wOh1bo2MqUOyxMbUfkHk%2BwKfsn40nNpF801PthDw64QzEHZduOg4&rqlang=cn&rsv_enter=1&rsv_sug3=2&rsv_sug1=2&rsv_sug7=100&rsv_n=2&rsv_sug2=0&inputT=748&rsv_sug4=1520\'
url = \'https://www.baidu.com/s\'
h2 = {
\'User-Agent\': \'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.81 Safari/537.36\'
}
res = requests.get(url, data, headers=h2)
# print(res.text)
html = etree.HTML(res.text)
# 百度搜索结果的每个连接装在列表中
ht = html.xpath(\'//h3[@class="t"]/*/@href\')
# print(ht)
li = []
for i in ht:
res_ = requests.get(i, headers=h2)
re = etree.HTML(res_.text)
f = re.xpath(\'//meta/@charset\')
# 如果编码是 utf8 的
if \'\'.join(f) == \'utf-8\' or \'\'.join(f) ==\'UTF-8\':
# print(1111)
# 以 utf8 编码得到 html
re = etree.HTML(res_.content.decode())
# 从 html 中匹配到可以被搜索引擎爬到的信息
p = re.xpath(\'//meta/@content\')
if p:
# p 为列表，用 join 方法转为 str，
# return \'\'.join(p)
li.append(\'\'.join(p))
elif \'\'.join(f) == \'gb2312\' or \'\'.join(f) ==\'gbk\' or \'\'.join(f) ==\'GBK\':
# print(2222)
re = etree.HTML(res_.content.decode(\'GBK\'))
p = re.xpath(\'//meta/@content\')
if p:
# p 为列表，用 join 方法转为 str，
# return \'\'.join(p)
li.append(\'\'.join(p))
# elif \'\'.join(f) == \'\':
# print(333)
# re = etree.HTML(res_.content.decode(\'GBK\'))
# p = re.xpath(\'//meta/@content\')
# if p:
# # p 为列表，用 join 方法转为 str，
# return \'\'.join(p)
return li
if __name__ == \'__main__\':
b = word_recognition.BaiDuAPI(\'co.ini\')
# 文字误国后得到列表
text = b.shi_bie(\'2.png\')
# 将列表里的元素的长度放入 l 的列表
l = []
for i in text:
l.append(len(i))
# print(l)
# 找出最长的元素
x =0
for i in range(len(l)):
if i+1 != len(l):
if l[i]>x:
x = l[i]
else:x = x
# 通过这个下标找到题目
tx =text [l.index(x)]
try:
print(\'题目是：\',tx)
print(\'正在百度搜索答案......\')
# 百度搜索得到列表 a
a = get_baidu(tx)
# 把列表拼接成字符串
a = \'\'.join(a)
# print(a)
if text [l.index(x)+1] in a:
print(\'答案是：1 \', text [l.index(x)+1] )
elif text [l.index(x)+2] in a:
print(\'答案是：2 \',text [l.index(x)+2])
elif text [l.index(x)+3] in a:
print(\'答案是：3 \',text [l.index(x)+3])
elif text [l.index(x)+4] in a:
print(\'答案是： 4 \',text [l.index(x)+4])
# print(\'\'.join(a))
except Exception as e:
print(\'找不到\')
百度文字识别 word_recognition
# -*- coding:utf-8 -*-
# 斌彬电脑
# @Time : 2018/9/9 0009 下午 2:00
import configparser # 读写配置文件
from aip import AipOcr # pip install baidu-aip 百度文字识别
class BaiDuAPI( object ): # 父类
\'\'\'用于文字识别\'\'\'
def __init__(self,filePath):
target = configparser.ConfigParser()
# 将百度得到 KEY 写入 co.ini，
target.read( filePath, encoding=\'utf-8-sig\' )
app_id = target.get(\'我的 KEY\',\'APP_ID\')
api_key = target.get(\'我的 KEY\',\'API_KEY\')
secret_key = target.get(\'我的 KEY\',\'SECRET_KEY\')
self.client = AipOcr(app_id, api_key, secret_key) # 百度提供
@staticmethod # 静态方法
def get_a(filePath):
\'\'\'用于读取图片\'\'\'
with open( filePath,\'rb\' ) as f:
return f.read()
def shi_bie(self,filePath):
\'\'\'将图片成文字\'\'\'
image = self.get_a(filePath)
texts = self.client.basicGeneral(image) # 百度提供
# print(texts)
# texts = texts[\'words_result\'][0][\'words\']
te = []
for i in texts[\'words_result\']:
# 取到最后，如果没有 words 返回 空
# te = te + \'\'.join(i.get(\'words\',\'\') )
te.append(i[\'words\'])
# print(te)
return te
if __name__ ==\'__main__\':
d = BaiDuAPI(\'co.ini\')
text = d.shi_bie(\'1.png\')
print(text[7])
print(text[8])
print(text[9])
print(text[10])
print(text[11])
co.ini
[我的 KEY]
APP_ID = 123
API_KEY = abcL
SECRET_KEY = dddu
;client = AipOcr(APP_ID, API_KEY, SECRET_KEY)
版权声明：本文为gdwz922原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。