python 爬取国家粮食局东北地区玉米收购价格监测信息

#!/usr/bin/python
# -*- coding: UTF-8 -*-
import re
import sys
import time
import urllib
import urllib.request
from datetime import datetime

def get_html(url):
    try:
        request = urllib.request.Request(url)
        WebPageContent = urllib.request.urlopen(request)
        return WebPageContent.read().decode('UTF-8')
    except urllib.error.HTTPError as e:
        print(e)
        return "Error"

def cbk(a, b, c):
    #显示当前下载进度
    persent = 100.00 * a * b / c
    if persent > 100:
        persent = 100
    sys.stdout.write("{0} %\r".format(round(persent,2)))
    sys.stdout.flush()
    
def get_image(WebPageContent, re_rule, output_path):
    image = re.compile(re_rule)
    image_url_list = re.findall(image, WebPageContent)
    for part_url in image_url_list:
        image_url = "%s%s.jpg" % ("http://www.chinagrain.gov.cn/", part_url)
    print(image_url)
    try:
        urllib.request.urlretrieve(url=image_url, filename=output_path, reporthook=cbk)
    except IsADirectoryError as e:
        print(e)
    
    

if __name__ == '__main__':
    #__init__
    url = "http://www.chinagrain.gov.cn/n787423/c1163380/content.html"
    re_rule = r'src="../../(.+?).jpg"'
    output_path = ""
    
    starttime = datetime.now()
    WebPageContent = get_html(url=url)
    #print(WebPageContent)
    get_image(WebPageContent=WebPageContent, re_rule=re_rule, output_path=output_path)
    endtime = datetime.now()
    print("Runtime is: %s s" % (endtime-starttime).seconds)

转载于:https://www.cnblogs.com/wangjunhaoBlog/p/8080099.html