Taobao commodity web crawler based on requests library and re library

Crawl designated product information on Taobao with python / only learning algorithm implementation

import requests
import re


def getHTMLText(url):
    try:
        Headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36',
            'Cookie': '******************************************************************'
        }
        r = requests.get(url, headers=Headers, timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return "网页请求失败"


def parsePage(ilt, html):
    try:
        plt = re.findall(r'\"view_price\"\:\"[\d\.]*\"', html)
        tlt = re.findall(r'\"raw_title\"\:\".*?\"', html)
        for i in range(len(plt)):
            price = eval(plt[i].split(':')[1])
            title = eval(tlt[i].split(':')[1])
            ilt.append([price, title])
    except:
        print("")


def printGoodsList(ilt):
    tplt = "{:^4}\t{:^8}\t{:16}"
    print(tplt.format("序号", "价格", "商品名称"))
    count = 0
    for g in ilt:
        count = count + 1
        print(tplt.format(count, g[0], g[1]))


def main():
    goods = "Python"
    depth = 2
    start_url = "https://s.taobao.com/search?q=" + goods
    infoList = []
    for i in range(depth):
        try:
            url = start_url + '&s=' + str(44 * i)
            html = getHTMLText(url)
            parsePage(infoList, html)
        except:
            continue
    print()
    printGoodsList(infoList)


main()

---

• Record learning