想爬取微信文章？

日常生活中，使用python语言，可以爬取搜狗微信的微信文章

搜狗微信：https://weixin.sogou.com/

爬取这些文章获取到每篇文章的标题和右侧的图片，将爬取到的图片以规定的命名方式输出到规定文件夹中，并将文章标题和图片名称对应输出到Excel和txt中 

 

 

 

 

Package                   Version

------------------------- ---------

altgraph                  0.17

certifi                   2020.6.20

chardet                   3.0.4

future                    0.18.2

idna                      2.10

lxml                      4.5.2

pefile                    2019.4.18

pip                       19.0.3

pyinstaller               4.0

pyinstaller-hooks-contrib 2020.8

pywin32-ctypes            0.2.0

requests                  2.24.0

setuptools                40.8.0

urllib3                   1.25.10

XlsxWriter                1.3.3

xlwt                      1.3.0


代码：# !/usr/bin/python

# -*- coding: UTF-8 -*-

import os

 

import requests

import xlsxwriter

from lxml import etree

 

# 请求微信文章的头部信息

headers = {

 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',

 'Accept-Encoding': 'gzip, deflate, br',

 'Accept-Language': 'zh-CN,zh;q=0.9',

 'Host': 'weixin.sogou.com',

 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.102 Safari/537.36'

}

# 下载图片的头部信息

headers_images = {

 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',

 'Accept-Encoding': 'gzip, deflate',

 'Accept-Language': 'zh-CN,zh;q=0.9',

 'Host': 'img01.sogoucdn.com',

 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.102 Safari/537.36'

}

a = 0

all = []

 

# 创建根目录

save_path = './微信文章'

folder = os.path.exists(save_path)

if not folder:

    os.makedirs(save_path)

# 创建图片文件夹

images_path = '%s/图片' % save_path

folder = os.path.exists(images_path)

if not folder:

    os.makedirs(images_path)

for i in range(1, 9):

 for j in range(1, 5):

        url = "https://weixin.sogou.com/pcindex/pc/pc_%d/%d.html" % (i, j)

 # 请求搜狗文章的url地址

        response = requests.get(url=url, headers=headers).text.encode('iso-8859-1').decode('utf-8')

 # 构造了一个XPath解析对象并对HTML文本进行自动修正

        html = etree.HTML(response)

 # XPath使用路径表达式来选取用户名

        xpath = html.xpath('/html/body/li')

 for content in xpath:

 # 计数

            a = a + 1

 # 文章标题

            title = content.xpath('./div[@class="txt-box"]/h3//text()')[0]

            article = {}

            article['title'] = title

            article['id'] = '%d.jpg' % a

            all.append(article)

 # 图片路径

            path = 'http:' + content.xpath('./div[@class="img-box"]//img/@src')[0]

 # 下载文章图片

            images = requests.get(url=path, headers=headers_images).content

 try:

 with open('%s/%d.jpg' % (images_path, a), "wb") as f:

                    print('正在下载第%d篇文章图片' % a)

                    f.write(images)

 except Exception as e:

                print('下载文章图片失败%s' % e)

# 信息存储在excel中

# 创建一个workbookx

workbook = xlsxwriter.Workbook('%s/Excel格式.xlsx' % save_path)

# 创建一个worksheet

worksheet = workbook.add_worksheet()

print('正在生成Excel...')

try:

 for i in range(0, len(all) + 1):

 # 第一行用于写入表头

 if i == 0:

            worksheet.write(i, 0, 'title')

            worksheet.write(i, 1, 'id')

 continue

        worksheet.write(i, 0, all[i - 1]['title'])

        worksheet.write(i, 1, all[i - 1]['id'])

    workbook.close()

except Exception as e:

    print('生成Excel失败%s' % e)

print("生成Excel成功")

print('正在生成txt...')

try:

 with open('%s/数组格式.txt' % save_path, "w") as f:

        f.write(str(all))

except Exception as e:

    print('生成txt失败%s' % e)

print('生成txt成功')

print('共爬取%d篇文章' % a)

 最后将程序打包成exe文件，在windows系统下可以直接运行程序

 

 进下面链接，学习更多python小技巧。

 https://note.youdao.com/s/bfdk7lCG