Question

我有一个代码可以获得三星级以上的前20名产品。我需要帮助为2000产品创造一些东西。请检查我的代码。我正在考虑获取亚马逊网站上页码的链接，并在我获得2000个产品之前进行循环，但无法弄清楚如何制作循环。这是我的代码：

import requests
from bs4 import BeautifulSoup
import re
headers = {'User-agent': 'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2062.120 Safari/537.36'}


def star_link():
    search = input("Please enter the category or search term: ")
    url1 = "https://www.amazon.in/s/ref=nb_sb_noss?url=search-alias%3Daps&field-keywords=" + search
    r1 = requests.get(url1)
    soup1 = BeautifulSoup(r1.text, 'lxml')
    links = soup1.find_all('i', 'a-star-3')
    for link in links:
        a_tag = link.parent
        a_link = a_tag['href']
    return a_link


def products():
    url2 = "https://www.amazon.in/"+star_link()
    r2  = requests.get(url2)
    soup2 = BeautifulSoup(r2.text, 'lxml')
    link_title = {}
    print('The top 2000 products of youe selected category with 3 stars and up are: ')
    print('\n')
    for n in range(0, 20):
        contents = soup2.findAll('li', id='result_' + str(n))
        for content in contents:
            links = [a['href'] for a in content.find_all(lambda i: i.get('href') and i.text)]
            titles = content.find_all('h2')
            for link in links:
                for title in titles:
                    link_title.update({title.text: link})
    for title in link_title:
        print(title + ':' + link_title[title])


products()

Answer 1

使用while True以无限循环方式运行，并在未获取数据时使用break

    data = soup.select('.result-info')
    if not data:
        print('END: no data:')
        break

BTW：

s=0

服务器也会提供首页，因此您无需查看if i == 0
s={}可以在?之后的任何地方 - 所以它可以在最后使代码更具可读性
您导入了csv模块，但您没有使用它我使用它并且我不需要replace(","," ")，因为如果项目中有" "，它会将文字放在,中。

完整代码

import requests
from bs4 import BeautifulSoup
import csv

filename = "output.csv"

f = open(filename, 'w', newline="", encoding='utf-8')

csvwriter = csv.writer(f)

csvwriter.writerow( ["Date", "Location", "Title", "Price"] )

offset = 0

while True:
    print('offset:', offset)

    url = "https://portland.craigslist.org/search/sss?query=xbox&sort=date&s={}".format(offset)

    response = requests.get(url)
    if response.status_code != 200:
        print('END: request status:', response.status)
        break

    soup = BeautifulSoup(response.text, 'html.parser')

    data = soup.select('.result-info')
    if not data:
        print('END: no data:')
        break

    for container in data:
        date = container.select('.result-date')[0].text

        try:
            location = container.select('.result-hood')[0].text
        except:
            try:
                location = container.select('.nearby')[0].text 
            except:
                location = ''
        #location = location.replace(","," ") # don't need it with `csvwriter`

        title = container.select('.result-title')[0].text

        try:
            price = container.select('.result-price')[0].text
        except:
            price = ''
        #title.replace(",", " ") # don't need it with `csvwriter`

        print(date, location, title, price)

        csvwriter.writerow( [date, location, title, price] )

    offset += 120

f.close()

如何使用beautifulsoup4用我的python脚本刮掉亚马逊的更多产品？

1 个答案: