如何通过多线程代码python提高Webscraping代码速度

Question

下面是我逐行编写的代码（大约有 900 页，每行有 10 行和 5 个数据） 有什么方法可以加快速度。目前将数据导出到 csv 需要 80 分钟。有什么方法可以对页面进行并行请求并提高此代码的效率。

import requests
from urllib3.exceptions import InsecureRequestWarning
import csv

requests.packages.urllib3.disable_warnings(InsecureRequestWarning)
from bs4 import BeautifulSoup as bs

f = csv.writer(open('GEM.csv', 'w', newline=''))
f.writerow(['Bidnumber', 'Items', 'Quantitiy', 'Department', 'Enddate'])


def scrap_bid_data():
    page_no = 1
    while page_no < 910:
        print('Hold on creating URL to fetch data...')
        url = 'https://bidplus.gem.gov.in/bidlists?bidlists&page_no=' + str(page_no)
        print('URL created: ' + url)
        scraped_data = requests.get(url, verify=False)
        soup_data = bs(scraped_data.text, 'lxml')
        extracted_data = soup_data.find('div', {'id': 'pagi_content'})
        if len(extracted_data) == 0:
            break
        else:
            for idx in range(len(extracted_data)):
                if (idx % 2 == 1):
                    bid_data = extracted_data.contents[idx].text.strip().split('\n')

                    bidno = bid_data[0].split(":")[-1]
                    items = bid_data[5].split(":")[-1]
                    qnty = int(bid_data[6].split(':')[1].strip())
                    dept = (bid_data[10] + bid_data[12].strip()).split(":")[-1]
                    edate = bid_data[17].split("End Date:")[-1]
                    f.writerow([bidno, items, qnty, dept, edate])

            page_no=page_no+1
scrap_bid_data()

Answer 1

我对您的代码进行了一些重组，以确保您的 CSV 文件已关闭。我还收到以下错误消息：

ConnectionError: HTTPSConnectionPool(host='bidplus.gem.gov.in', port=443): url: /bidlists?bidlists&page_no=1 超过最大重试次数（由 NewConnectionError('：建立新连接失败：[WinError 10060]连接尝试失败，因为连接方一段时间后没有正确响应，或者连接失败，因为连接的主机没有响应'，））

您应该尝试NUMBER_THREADS 值：

import requests
from urllib3.exceptions import InsecureRequestWarning
import csv
import concurrent.futures
import functools

requests.packages.urllib3.disable_warnings(InsecureRequestWarning)
from bs4 import BeautifulSoup as bs


def download_page(session, page_no):
    url = 'https://bidplus.gem.gov.in/bidlists?bidlists&page_no=' + str(page_no)
    print('URL created: ' + url)
    resp = session.get(url, verify=False)
    return resp.text


def scrap_bid_data():
    NUMBER_THREADS = 30 # number of concurrent download requests
    with open('GEM.csv', 'w', newline='') as out_file:
        f = csv.writer(out_file)
        f.writerow(['Bidnumber', 'Items', 'Quantitiy', 'Department', 'Enddate'])
        with requests.Session() as session:
            page_downloader = functools.partial(download_page, session)
            with concurrent.futures.ThreadPoolExecutor(max_workers=NUMBER_THREADS) as executor:
                pages = executor.map(page_downloader, range(1, 910))
                page_no = 0
                for page in pages:
                    page_no += 1
                    soup_data = bs(page, 'lxml')
                    extracted_data = soup_data.find('div', {'id': 'pagi_content'})
                    if extracted_data is None or len(extracted_data) == 0:
                        print('No data at page number', page_no)
                        print(page)
                        break
                    else:
                        for idx in range(len(extracted_data)):
                            if (idx % 2 == 1):
                                bid_data = extracted_data.contents[idx].text.strip().split('\n')

                                bidno = bid_data[0].split(":")[-1]
                                items = bid_data[5].split(":")[-1]
                                qnty = int(bid_data[6].split(':')[1].strip())
                                dept = (bid_data[10] + bid_data[12].strip()).split(":")[-1]
                                edate = bid_data[17].split("End Date:")[-1]
                                f.writerow([bidno, items, qnty, dept, edate])
scrap_bid_data()