#coding:utf-8
import werobot
import pymongoclass Gongzhonghao():def __init__(self,token,APP_ID,ENCODING_AES_KEY,APP_SECRET):self.robot = werobot.WeRoBot(token = token)self.robot.config['HOST'] = '0.0.0.0'self.robot.config['PORT'] = 80self.robot.config['APP_ID'] = APP_IDself.robot.config['ENCODING_AES_KEY'] = ENCODING_AES_KEYself.robot.config['APP_SECRET'] = APP_SECRETdef _getNews_Count(self):"""获取公众号图文消息总数:return: Int"""mediacount = self.robot.client.get_media_count()news_count = mediacount['news_count']return news_countdef getNews(self):"""获取公众号所有的图文内容:return: Json"""i = 0items = []news_count = self._getNews_Count()while i < news_count:tempj = self.robot.client.get_media_list('news', i, 20)items  = tempj['item'] + itemsi = i + 20j = {'total_count': news_count,'items': items}return jdef echo(self):"""用于公众号后台初次配置的验证:return: null"""self.robot.run()if __name__ == '__main__':g = Gongzhonghao('1', '2', '3','4') j = g.getNews()client = pymongo.MongoClient('ip', 27017)db = client.gongzhonghaoxxx= db.xxxxxx.insert(j)

# -*- coding:utf-8 -*-import os
import urllib.parse
from html.parser import HTMLParserimport requests
from bs4 import BeautifulSoup
from pymongo import MongoClientclass ContentHtmlParser(HTMLParser):"""过滤html标签"""def __init__(self):HTMLParser.__init__(self)self.text = ""def handle_data(self, data):self.text += datadef get_text(self):return self.textmongo_client = MongoClient("ip", 27017)
mongo_db = mongo_client["gongzhonghao"]def get_words():words = []with open("words.txt", encoding="utf-8") as words_file:for lines in words_file.readlines():if len(lines.strip()) == 0:continueif lines.find("、") != -1:for p in lines.split("、"):words.append(p.replace("\n", ""))else:words.append(lines.replace("\n", ""))return wordsdef get_articles(clt):articles = []collection = mongo_db[clt]doc = collection.find_one()items = doc["items"]for it in items:content = it["content"]["news_item"][0]articles.append(content)return articlesdef download(dir, file_name, url):if not os.path.exists(dir):os.mkdir(dir)try:resp = requests.get(url)path = dir + "\\" + file_nameif os.path.exists(path):returnwith open(path, "wb") as f:f.write(resp.content)except :print(url)def find_images(content):imgs = []c = urllib.parse.unquote(content)img_labels = BeautifulSoup(c, "html.parser").find_all("img")for img in img_labels:src = img.get("data-src")imgs.append(src)return imgsdef get_suffix(url):try:suffix = url[url.rindex("=") + 1:]if suffix == "jpeg" or suffix == "other":return ".jpg"return "." + suffixexcept:return ".jpg"def filter_content(content):parser = ContentHtmlParser()parser.feed(content)return parser.get_text()def check_jinyongci(content):fc = filter_content(content)words = get_words()invalids = []for w in words:if fc.find(w) != -1:invalids.append(w)return invalidsdef save_jinyongci(clt, title, invalids):if len(invalids) == 0:returnfile = clt + "\\invalid.txt"with open(file, "a+",encoding="utf-8") as f:f.write("标题：" + title)f.write("\r\n敏感词：")for iv in invalids:f.write(iv)f.write("、")f.write("\r\n\r\n")if __name__ == "__main__":clt = "xxx"if not os.path.exists(clt):os.mkdir(clt)articles = get_articles(clt)print(clt + ": 共" + str(len(articles)) + "个")for i in range(0, len(articles)):print("正在处理第 " + str(i) + " 个")title = articles[i]["title"]thumb_url = articles[i]["thumb_url"]content = articles[i]["content"]# 下载封面# path = os.path.join(clt, title)fname = str(i) + "_" + title.replace("|", "").replace("<", "").replace(">", "")download(clt, fname + get_suffix(thumb_url), thumb_url)# 找出文章中的图片imgs = find_images(content)index = 0for img in imgs:download(clt, fname + "_" + str(index) + get_suffix(img), img)index = index + 1# 找出文章中的敏感词invalids = check_jinyongci(content)print(invalids,'----',title)save_jinyongci(clt, title, invalids)

最大程度、最高级、最高端、最奢侈、最低级、最便宜、史上最低价、最流行、最受欢迎、最先进科学、最新技术、最新科学中国第一、全网第一、销量第一、排名第一、第一品牌、NO.1、TOP1、独一无二、全国第一、最后一波、大品牌之一、销冠国家级、国际级、世界级、千万级、百万级、星级、5A、甲级、超甲级顶级、尖端、顶尖、顶级享受、完美、至尊、空前、绝后、绝版、非此莫属、巅峰、前所未有、完美、翘楚之作、不可再生、不可复制、绝无仅有、寸土寸金、淋漓尽致、无与伦比、唯一、卓越前无古人后无来者、绝版、珍稀、臻稀、稀少、绝无仅有、绝不在有、稀世珍宝、千金难求、世所罕见、不可多得、空前绝后、寥寥无几、屈指可数独家、独创、独据、开发者、缔造者、创始者、发明者首个、首选、独家、首发、首席、首府、首选、首屈一指、全国首家、国家领导人、国门、国宅、首次、填补国内空白、国际品质大牌、金牌、名牌、王牌、领先上市、巨星、著名、掌门人、至尊、冠军世界领先、领先、领导者、领袖、引领、创领、领航、耀领史无前例、前无古人、永久、万能、百分之百