【Python与SEO】悟空问答自动采集及Zblog博客自动发布一条龙源码！

# 悟空问答采集处理
# -*- coding: utf-8 -*-
import requests, json
import re
import xmlrpc.client
from PIL import ImageFont, ImageDraw, Image
import time
import datetime
import os
import random
from requests.packages.urllib3.exceptions import InsecureRequestWarning

# 协议头列表
ua_list = [
    "Mozilla/5.0(compatible;Baiduspider-render/2.0; +http://www.baidu.com/search/spider.html)",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36; 360Spider",
    "Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)",
    "Mozilla/5.0 (compatible; YandexBot/3.0; +http://yandex.com/bots)",
    "Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML,like Gecko)Chrome/41.0.6633.1032 Mobile Safari/537.36;Bytespider;",
    "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.81 YisouSpider/5.0 Safari/537.36",
]

now = datetime.datetime.now()
s = now.strftime('%y%m%d')
fs = f'/www/wwwroot/xxxx.cn/zb_users/upload/{s}/'
os.makedirs(fs, exist_ok=True)


# 生成时间戳图片名
def create_img_name():
    """
    获取当前时间，生成时间戳
    以时间戳命名图片名
    """
    t = time.time()
    img_name = int(t)  # 秒级时间戳
    img_name = f'{img_name}.jpeg'
    return img_name


# 生成文件名
def create_wjm():
    """
    获取当前日期生成保存图片的文件夹名称
    """
    now = datetime.datetime.now()
    s = now.strftime('%y%m%d')
    # r'/www/wwwroot/xxxx.cn/zb_users/upload'

    print(s)
    return s


# 标题转图片
def write_txt_img(title, fs):
    """
    以文章标题和背景图片合成图片并保存图片文件
    """
    bgimg = Image.open(f'/www/wwwroot/PythonSEO/pwsh/{(random.randint(1, 309))}.png')
    draw = ImageDraw.Draw(bgimg)  # 读取
    fnt = ImageFont.truetype('/www/wwwroot/PythonSEO/pm.ttf', 50)  # 设置字体及大小
    draw.text((50, 150), title, fill='red', font=fnt)  # 写入文本1 位置坐标 颜色
    # bgimg.show()  # 显示图片
    bgimg = bgimg.convert("RGB")  # 改成三通道色
    img_name = create_img_name()
    bgimg.save(f'{fs}{img_name}')  # 保存图片
    print("文字写入图片成功！")
    return img_name


# 获取下拉词
def get_sug(word):
    """
    获取百度下拉词列表
    """
    # 禁用安全请求警告
    requests.packages.urllib3.disable_warnings(InsecureRequestWarning)
    url = 'https://sp0.baidu.com/5a1Fazu8AA54nxGko9WTAnF6hhy/su?wd=%s&sugmode=2&json=1&p=3&sid=1427_21091_21673_22581&req=2&pbs=%%E5%%BF%%AB%%E6%%89%%8B&csor=2&pwd=%%E5%%BF%%AB%%E6%%89%%8B&cb=jQuery11020924966752020363_1498055470768&_=1498055470781' % word
    r = requests.get(url, verify=False)  # 请求API接口，取消了HTTPS验证
    cont = r.content  # 获取返回的内容
    # print(cont)
    res = cont[41: -2].decode('gbk')  # 只取返回结果中json格式一段，并且解码为unicode
    res_json = json.loads(res)  # json格式转换
    keywords = res_json['s']
    print(keywords)
    return keywords  # 返回关键词列表


def get_qlist(word):
    """
    获取悟空问答列表，已失效！
    """
    headers = {'user-agent': random.choice(ua_list)}
    url = f"https://wukong.toutiao.com/wenda/web/question/association/?title={word}"
    response = requests.get(url=url, headers=headers, timeout=6)
    question_list = response.json()['question_list']
    if question_list:
        question = question_list[0]
        qtitle = question['title']
        img_name = write_txt_img(qtitle, fs)
        qid = question['qid']
        get_content(headers, word, qid, img_name, qtitle)
    else:
        path = r"/www/wwwroot/PythonSEO/fail.txt"
        con = f'{word}---{question_list}---获取悟空问答失败！-{datetime.datetime.now()}'
        save_txt(con, path)
    print(question)
    return question


# 获取问答详情
def get_content(headers, title, qid, img_name, name):
     """
    获取悟空问答详情，已失效！
    同时插入分类及发布文章数据
    """
    url = f"https://wukong.toutiao.com/wenda/web/question/loadmorev1/?qid={qid}&count=10"
    response = requests.get(url=url, headers=headers, timeout=6)
    print(response.status_code)
    ans_list = response.json()['data']['ans_list']
    if ans_list:
        print(f'有 {len(ans_list)} 个回答数据！')
        text = get_content_abstract_text(ans_list, img_name, name)
        # category = "品味生活"
        category = "品味生活"
        zbgfb(name, text[1], category, title, text[0])
    else:
        path = r"/www/wwwroot/PythonSEO/fail.txt"
        con = f'{title}---{ans_list}---获取悟空问答详情失败！-{datetime.datetime.now()}'
        save_txt(con, path)


# 回答数据处理,简介数据整合
def get_content_abstract_text(ans_list, img_name, name):
    """
    获取悟空问答数据规整简单合并处理
    """
    content = ''
    excerpt = ''
    for ans in ans_list:
        abstract_text = ans['abstract_text']
        # print(abstract_text) #简介
        abstract_texts = abstract_text.split('。')[:-1]
        abstext = '。'.join(abstract_texts)
        if abstext != '':
            print(abstext)
            excerpt = f'{excerpt}{abstext}'
            content = f"{content}{abstext}。</br>"

    exce = excerpt.split('。')
    excerpt = f'{name}{exce[0]},{exce[1]}。'
    result = add_html(content, img_name, name)
    print(result)
    text = excerpt, result
    return text


# 去除html代码标签
def re_html(content):
    pattern = re.compile(r'<[^>]+>', re.S)
    result = pattern.sub('', content)
    # print(result)
    return result


# 增加html代码标签
def add_html(content, img_name, name):
    img = f'<p style="text-align: center;"><img style="width: 600px; height: 400px;" src="http://www.xxxx.cn/zb_users/upload/{create_wjm()}/{img_name}" title="{name}" alt="{name}"></p>'
    # content=content.replace('。','。<br>').replace('?','?<br>').replace('!','!<br>')
    result = f'{img}<p>{content}</p>'
    # print(result)
    return result


# 发布文章
def zbgfb(title, content, category, key, excerpt):
    """
    zbolg博客接口发布文章
    """"
    username = "用户名"
    password = "密码"
    apiurl = "https://www.xxxx.cn/zb_system/xml-rpc/index.php"  # 接口地址填写自己zblog域名地址
    blogid = ''
    s = xmlrpc.client.ServerProxy(apiurl)  # 链接xmlrpc
    # print(s)
    keywords = get_sug(key)
    if keywords == []:
        blog = s.metaWeblog.newPost('', username, password, {
            'title': title,  # 标题
            'description': content,
            'categories': category,  # 分类
            'mt_keywords': key,  # 标签
            'mt_excerpt': excerpt,  # 摘要
        }, True)
    else:
        title = f'{title}-{keywords[0]}'
        bq = '<p style="font-size:12px;color:#8a92a9;"> 声明：网站作品（图文、音视频）源于网络分享，仅供网友学习交流。若您的权利被侵害，请联系 微信：huguo00289 删除！</p>'
        content = f'{content}<p>本文相关关键词：{key}，{keywords[1]}，{keywords[2]}</p>{bq}'
        blog = s.metaWeblog.newPost('', username, password, {
            'title': title,  # 标题
            'description': content,
            'categories': category,  # 分类
            'mt_keywords': key,  # 标签
            'mt_excerpt': excerpt,  # 摘要
        }, True)
    print(blog)
    print("发布文章成功！")
    path = r"/www/wwwroot/PythonSEO/pwshsuccess.txt"
    con = f'{key}---{title}'
    save_txt(con, path)


# 读取txt
def read_words():
    words = []
    with open('/www/wwwroot/PythonSEO/pwsh.txt', 'r', encoding='utf-8') as f:
        datas = f.readlines()
    print("读取关键词列表成功！")
    for data in datas:
        word = data.strip()
        word = word.replace('\n', '')
        words.append(word)
    return words


# 写入txt
def save_txt(word, path):
    with open(path, 'a+', encoding='utf-8') as f:
        f.write(f'{word}\n')


# 写入txt
def save_words(words):
    for word in words:
        with open('/www/wwwroot/PythonSEO/pwsh.txt', 'a+', encoding='utf-8') as f:
            f.write(f'{word}\n')
    print("更新关键词列表成功！")


def ts(url):
    """
    百度推送网页链接
    """
    apiurl = "http://data.zz.baidu.com/urls?site=https://www.xxxx.cn&token=dnTPOlAAkXIW876V"
    headers = {
        "User-Agent": "curl/7.12.1",
        "Host": "data.zz.baidu.com",
        "Content-Type": "text/plain",
        "Content-Length": "83",
    }
    response = requests.post(url=apiurl, data=url, headers=headers)
    print(response)
    print(response.json())


def tsll():
    """
    百度推送多条网页链接数据
    """
    url = "https://www.xxxx.cn/"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36",
    }
    html = requests.get(url=url, headers=headers, timeout=8).content.decode('utf-8')
    urls = re.findall(r'<h2><a href="(.+?)" target="_blank">', html, re.S)
    # print(len(urls))
    print(urls)
    for url in urls:
        with open("/www/wwwroot/PythonSEO/tsurls.txt", 'a+', encoding='utf-8') as f:
            f.write(f'{url}\n')
        ts(url)

    tag_html = requests.get(url=urls[0], headers=headers, timeout=8).content.decode('utf-8')
    id = re.findall(r"标签:                    <a href='https://www.xxxx.cn/tags-(.+?).html' title=", tag_html, re.S)[
        0]
    print(id)
    tag_urls = []
    tag_id = int(id)
    for i in range(1, 11):
        tag_url = f'https://www.xxxx.cn/tags-{tag_id}.html'
        tag_urls.append(tag_url)
        tag_id = tag_id - 1

    # print(len(tag_urls))
    print(tag_urls)
    for tag_url in tag_urls:
        with open("/www/wwwroot/PythonSEO/tsurls.txt", 'a+', encoding='utf-8') as f:
            f.write(f'{tag_url}\n')
        ts(tag_url)


def main():
    words = read_words()
    os.remove(r'/www/wwwroot/PythonSEO/pwsh.txt')  # 删除文件
    i = 0
    for word in words:
        word = word.replace('\ufeff', '')
        try:
            get_qlist(word)
            words.remove(word)
            i = i + 1
        except Exception as e:
            path = r"/www/wwwroot/PythonSEO/fail.txt"
            con = f'{word}---运行出错：{e}！-{datetime.datetime.now()}'
            save_txt(con, path)
            words.remove(word)
        time.sleep(random.randint(65, 140))
        if i > 8:
            tsll()  # 推送链接
            time.sleep(random.randint(120, 160))
        if i > 18:
            save_words(words)
            tsll()  # 推送链接
            break


if __name__ == '__main__':
    main()