Python识别html主要文本框过程解析

import requests
headers = {
  'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.106 Safari/537.36',
  'Host': 'blog.csdn.net'}
session = requests.session()
 
def getHtmlByRequests(url):
  headers.update(
    dict(Referer=url, Accept="*/*", Connection="keep-alive"))
  htmlContent = session.get(url=url, headers=headers).content
  return htmlContent.decode("utf-8", "ignore")

import re
# 统计中文字数
def countContent(string):
  pattern = re.compile(u'[\u1100-\uFFFD]+"htmlcode">

# 分析页面信息
def analyzeHtml(html):
  # 初始化网页
  soup = BeautifulSoup(html, "html.parser")
  part = soup.select('div')
  match = ""
  for paragraph in part:
    content = countContent(str(paragraph))
    if len(content) > len(match):
      match = str(paragraph)
  return match


得到主要的 div 后，提取里面的文字出来：


def main():
  url = "http://blog.csdn.net/"
  html = getHtmlByRequests(url)
  mainContent = analyzeHtml(html)
  soup = BeautifulSoup(mainContent, "html.parser")
  print(soup.select('div')[0].text)


完整的代码如下：


#!/usr/bin/env python
# -*- coding: utf-8 -*-

from bs4 import BeautifulSoup
import requests
import re

headers = {
  'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.106 Safari/537.36',
  'Host': 'blog.csdn.net'}
session = requests.session()


def getHtmlByRequests(url):
  headers.update(
    dict(Referer=url, Accept="*/*", Connection="keep-alive"))
  htmlContent = session.get(url=url, headers=headers).content
  return htmlContent.decode("utf-8", "ignore")

# 统计中文字数
def countContent(string):
  pattern = re.compile(u'[\u1100-\uFFFD]+"html.parser")
  part = soup.select('div')
  match = ""
  for paragraph in part:
    content = countContent(str(paragraph))
    if len(content) > len(match):
      match = str(paragraph)
  return match


def main():
  url = "http://blog.csdn.net/"
  html = getHtmlByRequests(url)
  mainContent = analyzeHtml(html)
  soup = BeautifulSoup(mainContent, "html.parser")
  print(soup.select('div')[0].text)


if __name__ == '__main__':
  main()


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。