获取股票在东财股吧的评论情况

import time
import datetime
import requests
import re
from bs4 import BeautifulSoup
from collections import OrderedDict
import hashlib
import tushare as ts
import logging

# import pandas as pd
# from pandas import DataFrame

# 最大查几天
rangemax = 7


def sortedDictValues3(adict):
    keys = adict.keys()
    keys.sort()
    return map(adict.get, keys)


def md5(str):
    m = hashlib.md5()
    m.update(str)
    returnstr = m.hexdigest()
    return returnstr.upper()


def matchguba_news(htmlcontent, allpost, allcomment):
    """匹配规则"""
    soup = BeautifulSoup(htmlcontent, "lxml")
    divs = soup.find_all(u"div", class_="articleh")
    divnu = 0
    date = ''
    for divitem in divs:
        a = str(divitem)
        # logging.info("====:%s"%a)
        if a.find("财经评论") == -1 and a.find("东方财富网") == -1:
            match = re.findall(r"<span class=\"l6\">(\d\d-\d\d)</span>", a)
            # logging.info(u"lydlyd:%s"%match)
            if match:
                timetemp = match[0]
                date = timetemp.replace('-', '')
                olddate = 0
                # if allpost.has_key(date):
                if date in allpost:
                    olddate = allpost[date]
                allpost[date] = olddate + 1
                oldcomment = 0
                matchcomment = re.findall(r"<span class=\"l2\">(\d+)</span>",
                                          a)
                # logging.info(matchcomment)
                # if allcomment.has_key(date):
                if date in allcomment:
                    oldcomment = allcomment[date]
                allcomment[date] = oldcomment + int(matchcomment[0])
    return date

# 构造 Request headers
agent = 'Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36'
headers = {
    'User-Agent':
    agent,
    'Host':
    "xueqiu.com",
    "Accept":
    "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
    "Accept-Encoding":
    "gzip, deflate, sdch, br",
    "Accept-Language":
    "zh-CN,zh;q=0.8,zh-TW;q=0.6",
    "Connection":
    "keep-alive"
}


def beginguba(stockname, stockscode, rangemaxgb):
    """开始抓取股吧"""
    logging.info("analyse stockcode:%s" % stockscode)
    # logging.info("要抓取的股吧股票为:%s" % stockname)
    logging.info(datetime.datetime.now())
    allpost = OrderedDict()
    allcomment = OrderedDict()
    for i in range(1, 100):
        urla = 'http://guba.eastmoney.com/list,%s,f_%d.html' % (stockscode, i)
        # logging.info(u"股吧数据第%d页,url:%s" % (i, urla))
        try:
            r = requests.get(url=urla)
            time.sleep(0.5)
            if r.status_code == 200:
                curdate = matchguba_news(r.content, allpost, allcomment)
                # 检查是否该break掉 (已经抓 到指定天数的数据时就break掉)
                if int(curdate) <= int(rangemaxgb[rangemaxgb.__len__() - 1]):
                    break
                time.sleep(1)
        except ValueError:
            logging.info('analyse stock %s failed'%stockscode)

    # newallpost = collections.OrderedDict(sorted(allpost.items(), key=lambda t: t[0]))
    if allpost.__len__() > 0:
        for datekey in allpost:
            if int(datekey) > int(rangemaxgb[rangemaxgb.__len__() - 1]):
                logging.info("issued_date:%s,number_of_posts:%d,general_comment_number:%d" %
                             (datekey, allpost[datekey], allcomment[datekey]))
    else:
        logging.info(u"no data,or analyse failed.")


def getstocknewscount(stockscode):
    tnow = time.localtime(time.time())
    rangemaxgb = [time.strftime('%m%d', tnow)]
    for i in range(1, rangemax + 1):
        t = time.localtime(time.time() - i * 86400)
        rangemaxgb.append(time.strftime('%m%d', t))

    # logging.info(rangemaxgb)
    # 设定抓取范围 抓取X天内的数据。直到抓到为止，最多100页
    urlbegin = 'http://guba.eastmoney.com/list,%s.html' % stockscode
    r = requests.get(url=urlbegin)
    soup = BeautifulSoup(r.content, "lxml")
    stockname = soup.title.string.split(u"_")[0]
    # 股吧数据获取开始
    beginguba(stockname, stockscode, rangemaxgb)


def main():
    # 记录到日志里
    logging.basicConfig(level=logging.DEBUG,
                format='%(asctime)s %(filename)s[line:%(lineno)d] %(levelname)s %(message)s',
                datefmt='%a, %d %b %Y %H:%M:%S',
                filename='stocknews.log',
                filemode='w')
    #定义一个StreamHandler，将INFO级别或更高的日志信息打印到标准错误，并将其添加到当前的日志处理对象#
    console = logging.StreamHandler()
    console.setLevel(logging.INFO)
    formatter = logging.Formatter('%(name)-12s: %(levelname)-8s %(message)s')
    console.setFormatter(formatter)
    logging.getLogger('').addHandler(console)


    logging.info('start guba comment count')

    # if len(sys.argv) > 1:
    #     stocklist = sys.argv[1].split(',')
    #     for stockcode in stocklist:
    #         getstocknewscount(stockcode)
    # else:
    #     logging.info(u"输入股票代码!")
    # quit()

    # 统计所有的股票
    logging.info(ts.__version__)
    df = ts.get_area_classified()
    for stockcode in df['code']:
        getstocknewscount(stockcode)

    logging.info('finished.')

    # stocklist = ['603337','300017','002665','002230','600566','600660','000957','000999','002304']
    # stocklist = ['300618', '300648', '603799']
    # for stockcode in stocklist:
    #     getstocknewscount(stockcode)


if __name__ == '__main__':
    main()

非常好的模式，让我今年收益翻倍的文章，强烈推荐：2020年4月至6月净利润断层实战小结-真香~