python3爬虫 链接+表格+图片（本地+csv+mongodb存储）

# -*- coding: utf-8 -*-
import requests
from bs4 import BeautifulSoup
import re
import csv
import time
from pymongo import MongoClient

client = MongoClient('localhost',27017)
db = client.admin 
db.authenticate("root", "root")
my_db = client.mydb  
col = my_db.zwfw_html  
link1 = 'http://www.hbzwfw.gov.cn/hbzw/sxcx/itemList/xz_index.do?webId=31&deptid='
def get_html(link):
    Cookie = "PHPStat_First_Time_10000011=1480428327337; PHPStat_Cookie_Global_User_Id=_ck16112922052713449617789740328; PHPStat_Return_Time_10000011=1480428327337; PHPStat_Main_Website_10000011=_ck16112922052713449617789740328%7C10000011%7C%7C%7C; VISITED_COMPANY_CODE=%5B%22600064%22%5D; VISITED_STOCK_CODE=%5B%22600064%22%5D; seecookie=%5B600064%5D%3A%u5357%u4EAC%u9AD8%u79D1; _trs_uv=ke6m_532_iw3ksw7h; VISITED_MENU=%5B%228451%22%2C%229055%22%2C%229062%22%2C%229729%22%2C%228528%22%5D"
    headers = {
        'User-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.106 Safari/537.36',
        'Cookie': Cookie,
        'Connection': 'keep-alive',
        'Accept': '*/*',
        'Accept-Language': 'zh-CN,zh;q=0.8',
        'Host': 'query.sse.com.cn',
        'Referer': 'http://www.sse.com.cn/assortment/stock/list/share/'
    }
    r = requests.get(link, headers=headers, timeout=10)
    if 200 != r.status_code:
        pass
    html = r.text
    return html

def get_id(link11):
    movie_list = []
    soup = BeautifulSoup(get_html(link=link11), "lxml")
    div_list2 = re.findall(r'href="javascript:changebm(.*)" title=(.*)',soup.decode("utf8", "ignore"))
    for i in range(len(div_list2)):
        list1 = str(div_list2[i])
        list2 = re.findall(r"[\u4e00-\u9fa5]+",list1)
        list3 = re.findall(r"\d+",list1)
        if len((list3[0]))==9:
            movie_list.append(list3[0])
        else:
            pass
    return movie_list

def get_shuju_1():
    movie_list2 = get_id(link1)
    print(movie_list2)
    for n in range(len(movie_list2)):
        try:
            url_id = movie_list2[n]
        except IndexError as e:
            pass
        for p in range(1,9):
            url3 = "http://www.hbzwfw.gov.cn/hbzw/sxcx/itemList/xz_list.do?webId=31&deptid=%s&isone=&isonline=&type=&word=&page_num=%s" % (url_id,p)
            soup3 = BeautifulSoup(get_html(link=url3), "lxml")
            div_list2 = soup3.select('a')
            if len(div_list2) != 0:
                print("存在此页" + '' + url3)
                div_list = soup3.select('div > div.r3_tit > a')
                for m in range(len(div_list)):
                    div_list_2 = str(div_list[m]).replace('<a href="', '').replace('" target="_blank" title="', '').replace('\r\n\t\t\t\t\t\t\t\t\t</a>', '')
                    div_list_3 = re.sub(r'">[\u4e00-\u9fa5]+', '', str(div_list_2))
                    pattern = re.compile(r'^http(.*)html')
                    div_list_4 = re.findall(pattern, div_list_3)
                    div_list_5 = re.findall(r"[\u4e00-\u9fa5,（,）,、,]+", div_list_3)
                    time.sleep(0.1)
                    movie_list3 = ('http'+str(div_list_4[0])+'html')
                    print(movie_list3, div_list_5[0])
                    save_contents(movie_list3,div_list_5[0])
                    dict_url = dict(zip(div_list_5[0],movie_list3))
                    col.insert(dict_url)
            else:
                None
def save_contents(shuju,title):
    urlist = shuju
    titleist = title
    try:
        with open("二级目录网址.csv",'a+',newline='') as f:
            writer = csv.writer(f)
            writer.writerows(zip([urlist], [titleist]))
    except:
        pass

if __name__ == '__main__':
    get_html(link=link1)
    get_shuju_1()