Python selenium爬取微信公众号文章代码详解

browser = webdriver.Chrome()
wait = WebDriverWait(browser,10)
# 随便访问一个地址，然后才能设置cookies
browser.get('https://httpbin.org/get')
# 添加cookies,df为保存的excel cookies
for i in range(len(df)):
  cookie_dict = {
          "domain": df.loc[i,'DomaiN'], 
          'name': df.loc[i,'Name'],
          'value': str(df.loc[i,'Value']),
          "expires": df.loc[i,"Expires/Max-Age"],
          'path': '/',}
  browser.add_cookie(cookie_dict)
browser.get(weixin_url)

<div class="loadmore with_line" style="display: none;" id="js_nomore">
    <div class="tips_wrp">
      <span class="tips js_no_more_msg" style="display: none;">已无更多</span>
      <span class="tips js_need_add_contact" style="display: none;">关注公众帐号，接收更多消息</span>
    </div>
  </div>

%%time
# 通过判断已无更多的style,来判断是否到最底部，最终执行到最底部
no_more_msg_style = 'display: none;'
while True:
  wait.until(EC.presence_of_element_located((By.XPATH,'//span[@class="tips js_no_more_msg" and text()="已无更多"]')))
  no_more= browser.find_element_by_xpath('//span[@class="tips js_no_more_msg" and text()="已无更多"]')
  now_style = no_more.get_attribute('style')
  if str(now_style).find(no_more_msg_style) == -1:
    # 说明已经加载完了
    break
  else:
    # 停顿一会，等待浏览器加载
    time.sleep(5)
    # 通过JS，执行到最底部
    browser.execute_script('window.scrollTo(0,document.body.scrollHeight)')

<div class="weui_msg_card js_card" msgid="1000000026">
      <div class="weui_msg_card_hd">2017年1月13日</div>
      <div class="weui_msg_card_bd">
         <!-- 图文 -->
             <!-- 普通图文 -->
            <div id="WXAPPMSG1000000026" class="weui_media_box appmsg js_appmsg" hrefs="http://mp.weixin.qq.com/s" data-t="0">
              <span class="weui_media_hd js_media" style="background-image:url(http://mmbiz.qpic.cn/mmbiz_jpg/XibhQ5tjv6dG9B4GF1C9MGBJO5AR2wvjCL9LgdcFgAdEgyU8wZFuDXoH9O9dNvafwK3RibCjUyiarIlUDlkxbcyfQ/640" data-s="640" hrefs="http://mp.weixin.qq.com/s" data-type="APPMSG">
              </span>
              <div class="weui_media_bd js_media" data-type="APPMSG">
                <h4 class="weui_media_title" hrefs="http://mp.weixin.qq.com/s">
                  承认自己是难民有什么错
                </h4>
                <p class="weui_media_desc">枷锁已经足够沉重，谢绝道德绑架</p>
                <p class="weui_media_extra_info">2017年1月13日</p>
              </div>
            </div> 
      </div>
    </div>

%%time
result = []
errlist = []
# 先得到其中一个
el_divs = browser.find_elements_by_xpath('//div[@class="weui_msg_card_list"]/div[@class="weui_msg_card js_card"]')
i = 0
for div in el_divs:
  date = title = url = yuanchuang = ''
  try:
    date = div.find_element_by_xpath('.//div[@class="weui_msg_card_hd"]').get_attribute('innerHTML')
    el_content = div.find_element_by_xpath('.//div[@class="weui_media_bd js_media"]')
    if el_content.get_attribute('data-type') == 'APPMSG':
      el = el_content.find_element_by_xpath('./h4[@class="weui_media_title"]')
      title = el.text
      url = el.get_attribute('hrefs')
      xb = el_content.find_element_by_xpath('./p[@class="weui_media_extra_info"]').text
      yuanchuang = '原创' if xb.find('原创') != -1 else ''
    elif el_content.get_attribute('data-type') == 'TEXT':
      title = '随文'
      url = el_content.find_element_by_xpath('./div').text
      yuanchuang = '原创'
    else:
      # 其他未能识别的类型
      errlist.append([i,div.get_attribute('innerHTML')])
  except NoSuchElementException:
    errlist.append([i,div.get_attribute('innerHTML')])
  print(str(i),':',date,title,url,yuanchuang)
  result.append([date,title,yuanchuang,url])
  i = i + 1