微信公众号文章采集工具，可采集文章文字内容信息及图片

上山打老虎

微信公众号文章采集工具，可采集文章文字内容信息及图片　　只能单篇采集，想要批量的不用看了！
可作为微信公众号文章图片采集助手使用！
　　需知：
1.exe程序运行环境为win7 64位操作系统！
2.部分文章图片采集存在BUG，望见谅！
3.工具为python编写，技术渣，只能到这里了！

　　微信公众号文章采集工具说明：
1.打开weixincj.exe文件
2.输入需要采集的微信公众号文章链接地址
3.回车等待程序运行
4.采集完毕5s后程序自动退出

　　采集过程中会自动生成目录 weixin
采集完毕，采集内容存放于weixin目录下的微信公众号文章标题目录
内容为图片及txt文档

　　下载地址
百度云：
链接: https://pan.baidu.com/s/1pCqptL6QwnP2eUeyAABnYA 提取码: sxca
　　需知：
exe程序运行环境为win7 64位操作系统！
　　提示：
不一定保证格式内容及图片完整性！
　　附上主要python源码：

#微信文章页采集
# -- coding: UTF-8 --
import requests
import re,time,os
from bs4 import BeautifulSoup
from baocun import bctp,bcwb
from fake_useragent import UserAgent
def ua():
  ua = UserAgent()
  headers = {"User-Agent": ua.random}
 return headers
def get_content(url):
  headers=ua()
respnese=requests.get(url,headers=headers).text
  soup=BeautifulSoup(respnese,'lxml')
  #获取标题
  h2=soup.find('h2',class_="rich_media_title").get_text()
  h2=h2.replace('\n','')
  h2 = h2.replace(' ', '')
  h2 = re.sub(r'[\|\/\<\>\:\*\?\\"]', "_", h2)  # 剔除不合法字符
  print(f'微信公众号文章标题：{h2}')
  os.makedirs(f'weixin/{h2}/',exist_ok=True)
  lj =f'weixin/{h2}/'
  ljj=f'weixin/{h2}/{h2}.txt'
  author=soup.find('div',class_="rich_media_meta_list").find('a',id="js_name").get_text()
  author = author.replace('\n', '')
  author = author.replace(' ', '')
  author=f'来源：{author}'
  print(author)
  i=1
  text=''
  ps=soup.find('div',class_="rich_media_content").find_all('p')
  for p in ps:
    <span class="token keyword">if</span> <span class="token string">"img"</span> <span class="token keyword">in</span> <span class="token builtin">str</span><span class="token punctuation">(</span>p<span class="token punctuation">)</span><span class="token punctuation">:</span>
      <span class="token keyword">try</span><span class="token punctuation">:</span>
        img_url<span class="token operator">=</span>p<span class="token punctuation">.</span>find<span class="token punctuation">(</span><span class="token string">'img'</span><span class="token punctuation">)</span><span class="token punctuation">[</span><span class="token string">'data-src'</span><span class="token punctuation">]</span>
        <span class="token keyword">print</span><span class="token punctuation">(</span>img_url<span class="token punctuation">)</span>
        <span class="token keyword">if</span> <span class="token string">"jpeg"</span> <span class="token operator">==</span> img_url<span class="token punctuation">[</span><span class="token operator">-</span><span class="token number">4</span><span class="token punctuation">:</span><span class="token punctuation">]</span><span class="token punctuation">:</span>
          img_name<span class="token operator">=</span>f<span class="token string">'{i}.{img_url[-4:]}'</span>
        <span class="token keyword">else</span><span class="token punctuation">:</span>
          img_name <span class="token operator">=</span> f<span class="token string">'{i}.{img_url[-3:]}'</span>
        bctp<span class="token punctuation">(</span>lj<span class="token punctuation">,</span> img_url<span class="token punctuation">,</span> img_name<span class="token punctuation">)</span>
        p_content<span class="token operator">=</span>img_name
        i<span class="token operator">=</span>i<span class="token operator">+</span><span class="token number">1</span>
      <span class="token keyword">except</span> Exception <span class="token keyword">as</span> e<span class="token punctuation">:</span>
        <span class="token keyword">print</span><span class="token punctuation">(</span>f<span class="token string">"获取图片数据失败，错误代码：{e}"</span><span class="token punctuation">)</span>
        <span class="token keyword">pass</span>
    <span class="token keyword">else</span><span class="token punctuation">:</span>
      p_content<span class="token operator">=</span>p<span class="token punctuation">.</span>get_text<span class="token punctuation">(</span><span class="token punctuation">)</span>
    text <span class="token operator">=</span> <span class="token string">'%s%s%s'</span> <span class="token operator">%</span> <span class="token punctuation">(</span>text<span class="token punctuation">,</span> <span class="token string">'\n'</span><span class="token punctuation">,</span>p_content<span class="token punctuation">)</span>
  texts<span class="token operator">=</span><span class="token string">'%s%s%s%s%s'</span><span class="token operator">%</span><span class="token punctuation">(</span>h2<span class="token punctuation">,</span><span class="token string">'\n'</span><span class="token punctuation">,</span>author<span class="token punctuation">,</span><span class="token string">'\n'</span><span class="token punctuation">,</span>text<span class="token punctuation">)</span>
  <span class="token keyword">print</span><span class="token punctuation">(</span>texts<span class="token punctuation">)</span>
  bcwb<span class="token punctuation">(</span>ljj<span class="token punctuation">,</span> texts<span class="token punctuation">)</span>

if __name__ == '__main__':    url=input("请输入要采集的微信公众号文章链接:")    print(f'爬虫启动中，请稍后......')    get_content(url)    print(f'采集完毕，程序5s后自动关闭！')    time.sleep(5)　　附改进 完整内容抓取，无格式

#微信公众号文章 完整版内容抓取
def cs(url):
  headers = ua()
respnese = requests.get(url, headers=headers).text
  soup = BeautifulSoup(respnese, 'lxml')
get_article(soup)
def get_article(soup):
  # 获取标题
  h2 = soup.find('h2', class_="rich_media_title").get_text()
  h2 = h2.replace('\n', '')
  h2 = h2.replace(' ', '')
  h2 = re.sub(r'[\|\/\<\>\:\*\?\\"]', "_", h2)  # 剔除不合法字符
  print(f'微信公众号文章标题：{h2}')
  os.makedirs(f'weixin/{h2}/', exist_ok=True)
  lj = f'weixin/{h2}/'
  ljj = f'weixin/{h2}/{h2}.txt'
  author = soup.find('div', class_="rich_media_meta_list").find('a', id="js_name").get_text()
  author = author.replace('\n', '')
  author = author.replace(' ', '')
  author = f'来源：{author}'
  print(author)
  # 获取文字内容
  texts = soup.find('div', class_="rich_media_content").get_text()
  texts = '\n'.join(texts.split('。'))  # 以句号 分割文本
  print(texts)
  texts = '%s%s%s%s%s' % (h2, '\n', author, '\n', texts)
  print(texts)
  bcwb(ljj, texts)
  # 获取所有图片
  i = 1
  imgs = soup.find('div', class_="rich_media_content").find_all('img')
  for img in imgs:
    img_url <span class="token operator">=</span> img<span class="token punctuation">[</span><span class="token string">'data-src'</span><span class="token punctuation">]</span>
    <span class="token keyword">print</span><span class="token punctuation">(</span>img_url<span class="token punctuation">)</span>
    <span class="token keyword">if</span> <span class="token string">"jpeg"</span> <span class="token operator">==</span> img_url<span class="token punctuation">[</span><span class="token operator">-</span><span class="token number">4</span><span class="token punctuation">:</span><span class="token punctuation">]</span><span class="token punctuation">:</span>
      img_name <span class="token operator">=</span> f<span class="token string">'{i}.{img_url[-4:]}'</span>
    <span class="token keyword">else</span><span class="token punctuation">:</span>
      img_name <span class="token operator">=</span> f<span class="token string">'{i}.{img_url[-3:]}'</span>
    bctp<span class="token punctuation">(</span>lj<span class="token punctuation">,</span> img_url<span class="token punctuation">,</span> img_name<span class="token punctuation">)</span>
    i <span class="token operator">=</span> i <span class="token operator">+</span> <span class="token number">1</span>

　　源码应用到的保存模块

#存储内容
import requests
import time
from fake_useragent import UserAgent
def ua():
  ua = UserAgent()
  headers = {"User-Agent": ua.random}
 return headers
#下载图片
def bctp(lj,img_url,img_name):
  print("开始下载图片！")
  try:
    r <span class="token operator">=</span> requests<span class="token punctuation">.</span>get<span class="token punctuation">(</span>img_url<span class="token punctuation">,</span>headers<span class="token operator">=</span>ua<span class="token punctuation">(</span><span class="token punctuation">)</span><span class="token punctuation">,</span>timeout<span class="token operator">=</span><span class="token number">5</span><span class="token punctuation">)</span>
    <span class="token keyword">with</span> <span class="token builtin">open</span><span class="token punctuation">(</span>f<span class="token string">'{lj}/{img_name}'</span><span class="token punctuation">,</span> <span class="token string">'wb'</span><span class="token punctuation">)</span> <span class="token keyword">as</span> f<span class="token punctuation">:</span>
      f<span class="token punctuation">.</span>write<span class="token punctuation">(</span>r<span class="token punctuation">.</span>content<span class="token punctuation">)</span>
      <span class="token keyword">print</span><span class="token punctuation">(</span>f<span class="token string">'下载{img_name}图片成功！'</span><span class="token punctuation">)</span>
      time<span class="token punctuation">.</span>sleep<span class="token punctuation">(</span><span class="token number">1</span><span class="token punctuation">)</span>
  <span class="token keyword">except</span> Exception <span class="token keyword">as</span> e<span class="token punctuation">:</span>
    <span class="token keyword">if</span> <span class="token string">"port=443): Read timed out"</span> <span class="token keyword">in</span> <span class="token builtin">str</span><span class="token punctuation">(</span>e<span class="token punctuation">)</span><span class="token punctuation">:</span>
      time<span class="token punctuation">.</span>sleep<span class="token punctuation">(</span><span class="token number">2</span><span class="token punctuation">)</span>
      <span class="token keyword">try</span><span class="token punctuation">:</span>
        r <span class="token operator">=</span> requests<span class="token punctuation">.</span>get<span class="token punctuation">(</span>img_url<span class="token punctuation">,</span> headers<span class="token operator">=</span>ua<span class="token punctuation">(</span><span class="token punctuation">)</span><span class="token punctuation">,</span>timeout<span class="token operator">=</span><span class="token number">5</span><span class="token punctuation">)</span>
        <span class="token keyword">with</span> <span class="token builtin">open</span><span class="token punctuation">(</span>f<span class="token string">'{lj}/{img_name}'</span><span class="token punctuation">,</span> <span class="token string">'wb'</span><span class="token punctuation">)</span> <span class="token keyword">as</span> f<span class="token punctuation">:</span>
          f<span class="token punctuation">.</span>write<span class="token punctuation">(</span>r<span class="token punctuation">.</span>content<span class="token punctuation">)</span>
          <span class="token keyword">print</span><span class="token punctuation">(</span>f<span class="token string">'下载{img_name}图片成功！'</span><span class="token punctuation">)</span>
      <span class="token keyword">except</span> Exception <span class="token keyword">as</span> e<span class="token punctuation">:</span>
        <span class="token keyword">print</span><span class="token punctuation">(</span>f<span class="token string">'下载{img_name}图片失败！'</span><span class="token punctuation">)</span>
        <span class="token keyword">print</span><span class="token punctuation">(</span>f<span class="token string">'错误代码：{e}'</span><span class="token punctuation">)</span>
        <span class="token keyword">with</span> <span class="token builtin">open</span><span class="token punctuation">(</span>f<span class="token string">'{lj}/spider.txt'</span><span class="token punctuation">,</span> <span class="token string">'a+'</span><span class="token punctuation">,</span> encoding<span class="token operator">=</span><span class="token string">'utf-8'</span><span class="token punctuation">)</span> <span class="token keyword">as</span> f<span class="token punctuation">:</span>
          f<span class="token punctuation">.</span>write<span class="token punctuation">(</span>f<span class="token string">'错误代码：{e}---下载 {img_url} 图片失败\n'</span><span class="token punctuation">)</span>
    <span class="token keyword">else</span><span class="token punctuation">:</span>
      <span class="token keyword">print</span><span class="token punctuation">(</span>f<span class="token string">'下载{img_name}图片失败！'</span><span class="token punctuation">)</span>
      <span class="token keyword">print</span><span class="token punctuation">(</span>f<span class="token string">'错误代码：{e}'</span><span class="token punctuation">)</span>
      <span class="token keyword">with</span> <span class="token builtin">open</span><span class="token punctuation">(</span>f<span class="token string">'{lj}/spider.txt'</span><span class="token punctuation">,</span> <span class="token string">'a+'</span><span class="token punctuation">,</span> encoding<span class="token operator">=</span><span class="token string">'utf-8'</span><span class="token punctuation">)</span> <span class="token keyword">as</span> f<span class="token punctuation">:</span>
        f<span class="token punctuation">.</span>write<span class="token punctuation">(</span>f<span class="token string">'错误代码：{e}---下载 {img_url} 图片失败\n'</span><span class="token punctuation">)</span>

#保存文本内容def bcwb(ljj,texts):    print("开始保存文本")    with open(ljj, 'w', encoding='utf-8') as f:

f<span class="token punctuation">.</span>write<span class="token punctuation">(</span>texts<span class="token punctuation">)</span>
  <span class="token keyword">print</span><span class="token punctuation">(</span>f<span class="token string">'保存文本内容成功！'</span><span class="token punctuation">)</span>