Python實現快速保存微信公眾號文章中的圖片

import requests
from re import findall
from bs4 import BeautifulSoup
import time
import os
import sys


weixin_title=""
weixin_time=""

#獲取微信公眾號內容,保存標題和時間
def get_weixin_html(url):
    global weixin_time,weixin_title
    res=requests.get(url)
    soup=BeautifulSoup(res.text,"html.parser")
    
    #獲取標題
    temp=soup.find('h1')
    weixin_title=temp.string.strip()
    
    #使用正則表達式獲取時間
#    result=findall(r'[0-9]{4}-[0-9]{2}-[0-9]{2}.+:[0-9]{2}',res.text)
    result=findall(r"(\d{4}-\d{1,2}-\d{1,2})",res.text)
    weixin_time=result[0]
    
    #獲取正文html並修改
    content=soup.find(id='js_content')
    soup2=BeautifulSoup((str(content)),"html.parser")
    soup2.div['style']='visibility: visible;'
    html=str(soup2)
    pattern=r'http[s]?:\/\/[a-z.A-Z_0-9\/\?=-_-]+'
    result = findall(pattern, html)
    
    #將data-src修改為src
    for url in result:
        html=html.replace('data-src="'+url+'"','src="'+url+'"')
    
    return html

#上傳圖片至服務器
def download_pic(content):
    
    pic_path= 'pic/' + str(path)+ '/'
    if not os.path.exists(pic_path):
        os.makedirs(pic_path)
        
    #使用正則表達式查找所有需要下載的圖片鏈接
    pattern=r'http[s]?:\/\/[a-z.A-Z_0-9\/\?=-_-]+'
    pic_list = findall(pattern, content)
    
    for index, item in enumerate(pic_list,1):
        count=1
        flag=True
        pic_url=str(item)
        
        while flag and count<=10:
            try:
                 data=requests.get(pic_url);
   
                 if pic_url.find('png')>0:
                     file_name = str(index)+'.png'
                     
                 elif pic_url.find('gif')>0:
                     file_name=str(index)+'.gif'
                     
                 else:
                     file_name=str(index)+'.jpg'

                 with open( pic_path + file_name,"wb") as f:
                     f.write(data.content)
                     
                 #將圖片鏈接替換為本地鏈接
                 content = content.replace(pic_url, pic_path + file_name)
                 
                 flag = False
                 print('已下載第' + str(index) +'張圖片.')
                 count += 1
                 time.sleep(1)
                      
            except:
                 count+=1
                 time.sleep(1)
                 
        if count>10:
            print("下載出錯：",pic_url)
    return content


def get_link(dir):
    link = []
    with open(dir,'r') as file_to_read:
        while True:
            line = file_to_read.readline()
            if not line:
                break
            line = line.strip('\n')
            link.append(line)
    return link

path = 'link.txt'
linklist = get_link(path)
print(linklist)
s = len(linklist)
        

if __name__ == "__main__":
    
    #獲取html
    input_flag=True
    while input_flag:
#        for j in range(0,s):
#            pic = str(j)
        j = 1
        for i in linklist:
            weixin_url = i  
            path = j
            j += 1     
            #weixin_url=input()
            re=findall(r'http[s]?:\/\/mp.weixin.qq.com\/s\/[0-9a-zA-Z_]+',weixin_url) 
            if len(re)<=0:
                    print("鏈接有誤，請重新輸入!")
            else:
                input_flag=False
            
            content=get_weixin_html(weixin_url)
            content=download_pic(content)
            #保存至本地
            with open(weixin_title+'.txt','w+',encoding="utf-8") as f:
                f.write(content) 
            with open(weixin_title+'.html','w+',encoding="utf-8") as f:
                f.write(content)  
                
            print()
            print("標題：《"+weixin_title+"》")
            print("發佈時間："+weixin_time)

import re
from datetime import datetime

test_date = '小明的生日是2016-12-12 14:34,小張的生日是2016-12-21 11:34 .'
test_datetime = '小明的生日是2016-12-12 14:34,.小晴的生日是2016-12-21 11:34,好可愛的.'

# date
mat = re.search(r"(\d{4}-\d{1,2}-\d{1,2})",test_date)
print mat.groups()
# ('2016-12-12',)
print mat.group(0)
# 2016-12-12

date_all = re.findall(r"(\d{4}-\d{1,2}-\d{1,2})",test_date)
for item in date_all:
    print item
# 2016-12-12
# 2016-12-21

# datetime
mat = re.search(r"(\d{4}-\d{1,2}-\d{1,2}\s\d{1,2}:\d{1,2})",test_datetime)
print mat.groups()
# ('2016-12-12 14:34',)
print mat.group(0)
# 2016-12-12 14:34

date_all = re.findall(r"(\d{4}-\d{1,2}-\d{1,2}\s\d{1,2}:\d{1,2})",test_datetime)
for item in date_all:
    print item
# 2016-12-12 14:34
# 2016-12-21 11:34
## 有效時間

# 如這樣的日期2016-12-35也可以匹配到.測試如下.
test_err_date = '如這樣的日期2016-12-35也可以匹配到.測試如下.'
print re.search(r"(\d{4}-\d{1,2}-\d{1,2})",test_err_date).group(0)
# 2016-12-35

# 可以加個判斷
def validate(date_text):
    try:
        if date_text != datetime.strptime(date_text, "%Y-%m-%d").strftime('%Y-%m-%d'):
            raise ValueError
        return True
    except ValueError:
        # raise ValueError("錯誤是日期格式或日期,格式是年-月-日")
        return False

print validate(re.search(r"(\d{4}-\d{1,2}-\d{1,2})",test_err_date).group(0))
# false

# 其他格式匹配. 如2016-12-24與2016/12/24的日期格式.
date_reg_exp = re.compile('\d{4}[-/]\d{2}[-/]\d{2}')

test_str= """
     平安夜聖誕節2016-12-24的日子與去年2015/12/24的是有不同哦.
     """
# 根據正則查找所有日期並返回
matches_list=date_reg_exp.findall(test_str)

# 列出並打印匹配的日期
for match in matches_list:
  print match

# 2016-12-24
# 2015/12/24