import requests
import re
from fontTools.ttLib import TTFont
from lxml import etree
from aip import AipOcr #pip install baidu-aip
url = "https://www.gxrc.com/jobDetail/d2f81ae03d34449396cb9e33dd7fe188"
response = requests.get(url=url)
response.encoding = 'utf-8'
html_data = response.text
selector = etree.HTML(html_data)
x1='//*[@id="jobDetail"]/div[2]/div[1]/div[1]/div[5]/div[2]/p[2]/label/img/@src' #联系电话
src_url="https:"+selector.xpath(x1)[0]
print(src_url)
r=requests.get(src_url)
i=0
with open('D:/zhusc/ps/{}.jpg'.format(str(i)),'wb') as f:
f.write(r.content)
#定义常量
APP_ID = '个人隐私'
API_KEY = '个人隐私'
SECRET_KEY = '个人隐私'
# 初始化AipFace对象
client = AipOcr(APP_ID, API_KEY, SECRET_KEY)
# 读取图片
def get_file_content(filePath):
with open(filePath, 'rb') as fp:
return fp.read()
image = get_file_content('D:/zhusc/ps/{}.jpg'.format(str(i)))
res = client.basicAccurate(image)
try:
print(res['words_result'][0]['words']) #输出识别结果
except:
print("联系电话不存在")
识别广西人才网联系电话
最新推荐文章于 2024-09-22 17:12:26 发布
这段代码演示了如何使用Python的requests库爬取网页,并通过lxml解析HTML找到电话号码的图片源。接着,利用百度OCR API进行图像识别,将识别出的电话号码打印出来。整个过程涉及网页抓取、图像下载和文字识别技术。
摘要由CSDN通过智能技术生成