中国证券投资基金业协会爬取

爬取要求：

网页爬取范围：5875页-尾页；
基金名称点击进去的二级页面！需要提取《基金类型》、《管理类型》两个字段；
私募基金管理人名称点进去的二级页面，需要提取《登记时间》、《成立时间》字段；
二级页面的四个字段跟到列表页后面形成表格。

代码：

import codecs
import csv
from lxml import etree
import requests
import random
import json
import time
import pandas as pd
import threading


# 输入毫秒级的时间，转出正常格式的时间
def timeStamp(timeNum):
    timeStamp = float(timeNum / 1000)
    timeArray = time.localtime(timeStamp)
    otherStyleTime = time.strftime("%Y-%m-%d %H:%M:%S", timeArray)
    return otherStyleTime


def save(rows):
    with codecs.open('证券.csv', 'ab', encoding='utf8') as f:
        writer = csv.writer(f)
        writer.writerows(rows)


baocuo_list = []


def craw(num):
    rows = []
    try:
        print('开始爬取=========', num)
        headers = {
            'Accept': 'application/json,text/javascript,*/*; q=0.01',
            'Accept-Encoding': 'gzip,deflate',
            'Connection': 'keep-alive',
            'Host': 'gs.amac.org.cn',
            'Content-Type': 'application/json;charset=UTF-8',
            'Origin': 'http://gs.amac.org.cn',
            'X-Requested-With': 'XMLHttpRequest',
            'Referer': 'http://gs.amac.org.cn/amac-infodisc/res/pof/fund/index.html',
            'User-Agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.135 Mobile Safari/537.36'
        }
        r = random.random()
        url = "http://gs.amac.org.cn/amac-infodisc/api/pof/fund?rand=" + str(r) + "&page=" + str(num) + "&size=20"
        data = {}
        data = json.dumps(data)
        response = requests.post(url=url, data=data, headers=headers)
        data_list = json.loads(response.text)["content"]
        count = 0
        for data in data_list:
            # print(data)
            fund_name = data['fundName']
            manager_name = data['managerName']
            mandator_name = data['mandatorName']
            establishDate = timeStamp(data['establishDate'])
            putOnRecordDate = str(establishDate)[:11]
            count += 1
            # 中国证券投资基金业协会提示地址
            url = 'http://gs.amac.org.cn/amac-infodisc/res/pof/fund/' + data['url']
            manager_url = 'http://gs.amac.org.cn/amac-infodisc/res/pof/' + data.get('managerUrl')[3:]
            response = requests.get(url=url, headers=headers)
            response.encoding = 'utf-8'
            # 管理类型
            manager_type = data['managerType']
            # 基金类型
            text = response.text
            text = etree.HTML(text)
            basic_type = 
                text.xpath('/ html / body / div[3] / div / div[2] / div[1] / div / table / tbody')[0].xpath(
                    'string(.)').strip().split(":")
            a = 0

            for i in basic_type:
                if '基金类型' in i:
                    a = basic_type.index(i)
            basic_type = basic_type[a + 1]
            basic_type = basic_type.split()[0].strip()

            # 备案时间
            beian_time = 
                text.xpath('/ html / body / div[3] / div / div[2] / div[1] / div / table / tbody / tr[4] / td[2]')[
                    0].xpath(
                    'string(.)').replace(
                    '
', '').replace(" ", "").replace("	", "")
            response = requests.get(url=manager_url, headers=headers)
            response.encoding = 'utf-8'
            text = response.text
            text = etree.HTML(text)
            # 成立时间
            establish_time = 
                text.xpath('/ html / body / div[3] / div / div[4] / div[2] / div[2] / table / tbody / tr[6] / td[2]')[
                    0].xpath('string(.)').replace(
                    '
', '').replace(" ", "").replace("	", "").split(':')[-1]
            # 登记时间
            register_time = text.xpath('/html/body/div[3]/div/div[4]/div[2]/div[2]/table/tbody/tr[5]/td[2]')[0].xpath(
                'string(.)').replace(
                '
', '').replace(" ", "").replace("	", "").split(':')[-1]
            row = (
                fund_name, manager_name, mandator_name, putOnRecordDate, beian_time, basic_type, manager_type,
                register_time,
                establish_time)
            rows.append(row)
            if num in baocuo_list:
                baocuo_list.pop(num)


        if len(rows) > 0:
            save(rows)
        print('爬取完成==========', num)
    except Exception as e:
        print('爬不了的======', num)
        print('爬不了的原因======', e)
        baocuo_list.append(num)


if __name__ == '__main__':
    with codecs.open('证券.csv', 'ab', encoding='utf8') as f:
        writer = csv.writer(f)
        writer.writerow(["基金名称", "私募基金管理人名称", "托管人名称", "成立时间", "备案时间", "基金类型", "管理类型", "登记时间", "成立时间-管理人"])
    for num in range(5874, 6620):
        t = threading.Thread(target=craw, args=(num,))
        t.start()
        t.join()

    print(baocuo_list)
    while 1:
        for i in baocuo_list:
            print('重新爬取===========', i)
            t = threading.Thread(target=craw, args=(i,))
            t.start()
            t.join()
            if len(baocuo_list) <= 0:
                break
        if len(baocuo_list) <= 0:
            break