python下载微信公众号相关文章

本文实例为大家分享了python下载微信公众号相关文章的具体代码，供大家参考，具体内容如下

目的：从零开始学自动化测试公众号中下载“pytest"一系列文档

1、搜索微信号文章关键字搜索

2、对搜索结果前n页进行解析，获取文章标题和对应url

主要使用的是requests和bs4中的beautifulsoup

weixin.py

import requests
from urllib.parse import quote
from bs4 import beautifulsoup
import re
from weixinspider.html2doc import myhtmlparser
 
class weixinspider(object):
 
 def __init__(self, gzh_name, pageno,keyword):
  self.gzh_name = gzh_name
  self.pageno = pageno
  self.keyword = keyword.lower()
  self.page_url = []
  self.article_list = []
  self.headers = {
   'user-agent': 'mozilla/5.0 (windows nt 10.0; wow64) applewebkit/537.36 (khtml, like gecko) chrome/70.0.3538.110 safari/537.36'}
  self.timeout = 5
  # [...] 用来表示一组字符,单独列出：[amk] 匹配 'a'，'m'或'k'
  # re+ 匹配1个或多个的表达式。
  self.pattern = r'[\\/:*?"<>|\r\n]+'
 
 def get_page_url(self):
  for i in range(1,self.pageno+1):
   # https://weixin.sogou.com/weixin?query=从零开始学自动化测试&_sug_type_=&s_from=input&_sug_=n&type=2&page=2&ie=utf8
   url = "https://weixin.sogou.com/weixin?query=%s&_sug_type_=&s_from=input&_sug_=n&type=2&page=%s&ie=utf8" \
     % (quote(self.gzh_name),i)
   self.page_url.append(url)
 
 def get_article_url(self):
  article = {}
  for url in self.page_url:
   response = requests.get(url,headers=self.headers,timeout=self.timeout)
   result = beautifulsoup(response.text, 'html.parser')
   articles = result.select('ul[class="news-list"] > li > div[class="txt-box"] > h3 > a ')
   for a in articles:
    # print(a.text)
    # print(a["href"])
    if self.keyword in a.text.lower():
      new_text=re.sub(self.pattern,"",a.text)
      article[new_text] = a["href"]
      self.article_list.append(article)
 
 
 
headers = {'user-agent':
      'mozilla/5.0 (windows nt 10.0; wow64) applewebkit/537.36 (khtml, like gecko) chrome/70.0.3538.110 safari/537.36'}
timeout = 5
gzh_name = 'pytest文档'
my_gzh = weixinspider(gzh_name,5,'pytest')
my_gzh.get_page_url()
# print(my_gzh.page_url)
my_gzh.get_article_url()
# print(my_gzh.article_list)
for article in my_gzh.article_list:
 for (key,value) in article.items():
  url=value
  html_response = requests.get(url,headers=headers,timeout=timeout)
  myhtmlparser = myhtmlparser(key)
  myhtmlparser.feed(html_response.text)
  myhtmlparser.doc.save(myhtmlparser.docfile)

html2doc.py

from html.parser import htmlparser
import requests
from docx import document
import re
from docx.shared import rgbcolor
import docx
 
 
class myhtmlparser(htmlparser):
 def __init__(self,docname):
  htmlparser.__init__(self)
  self.docname=docname
  self.docfile = r"d:\pytest\%s.doc"%self.docname
  self.doc=document()
  self.title = false
  self.code = false
  self.text=''
  self.processing =none
  self.codeprocessing =none
  self.picindex = 1
  self.headers = {
   'user-agent': 'mozilla/5.0 (windows nt 10.0; wow64) applewebkit/537.36 (khtml, like gecko) chrome/70.0.3538.110 safari/537.36'}
  self.timeout = 5
 
 def handle_startendtag(self, tag, attrs):
  # 图片的处理比较复杂，首先需要找到对应的图片的url，然后下载并写入doc中
  if tag == "img":
   if len(attrs) == 0:
    pass
   else:
    for (variable, value) in attrs:
     if variable == "data-type":
      picname = r"d:\pytest\%s%s.%s" % (self.docname, self.picindex, value)
      # print(picname)
     if variable == "data-src":
      picdata = requests.get(value, headers=self.headers, timeout=self.timeout)
      # print(value)
    self.picindex = self.picindex + 1
    # print(self.picindex)
    with open(picname, "wb") as pic:
     pic.write(picdata.content)
    try:
     self.doc.add_picture(picname)
    except docx.image.exceptions.unexpectedendoffileerror as e:
     print(e)
 
 def handle_starttag(self, tag, attrs):
  if re.match(r"h(\d)", tag):
   self.title = true
  if tag =="p":
   self.processing = tag
  if tag == "code":
   self.code = true
   self.codeprocessing = tag
 
 def handle_data(self, data):
   if self.title == true:
    self.doc.add_heading(data, level=2)
   # if self.in_div == true and self.tag == "p":
   if self.processing:
    self.text = self.text + data
   if self.code == true:
    p =self.doc.add_paragraph()
    run=p.add_run(data)
    run.font.color.rgb = rgbcolor(111,111,111)
 
 def handle_endtag(self, tag):
  self.title = false
  # self.code = false
  if tag == self.processing:
   self.doc.add_paragraph(self.text)
 
   self.processing = none
   self.text=''
  if tag == self.codeprocessing:
   self.code =false

运行结果：

缺少部分文档，如pytest文档4，是因为搜狗微信文章搜索结果中就没有

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持。