Question

我正在尝试从amazon.com的搜索结果中删除数据

现在，对于相同的关键字，亚马逊会返回<ul>标记中显示的结果列表。

每个<li>标记都包含结果中的产品。

当您从浏览器进行关键字搜索时，您会得到15个结果的列表，其中最后2或3个<li>是该列表中产品的“赞助”广告。

然而，使用beautifulsoup从python做同样的事情，我只得到<li> s不是“赞助”广告

我确保我没有错过标签，将整个汤打印在文件中并进行搜索。

这是运行bs4的python代码（你不会发现它在识别问题时非常有帮助，我很确定这是某种与亚马逊有关的东西）

def get_asins_in_page(soup, sponsored):
    asins_dict = {}
    asins_sponsored_dict = {}
    reslist = soup.find("ul", {"id": "s-results-list-atf"})
    for r in reslist.find_all('li'):
        asins_dict[r.get('data-asin')] = r.get('id')
    return asins_dict

def find_ranking_by_asin(keyword, target_asin, sponsored):
    print "%s %s"%(keyword, target_asin)
    loop_count = 0
    url = "http://www.amazon.com/s/?url=search-alias%3Daps&field-keywords="+urllib.quote(keyword)
    while True:
        loop_count+=1
        r = requests.get(url)
        data = r.text
        soup = BeautifulSoup(data)
        url ="http://www.amazon.com" + soup.find("a",{"id":"pagnNextLink"}).get('href') #next_page_url 
        asins_dict = get_asins_in_page(soup, False)
        if target_asin in asins_dict:
            return asins_dict[target_asin].replace("result_","")    
        #fail-safe:
        if loop_count > 50:
            return -1

我来自数据科学背景，所以我不是一个Web开发人员。可能是因为我错过了一些东西要告诉亚马逊我来自某种类型的网络浏览器！

编辑：我在请求中添加了标题，但仍然没有运气。

这里是带有标题的修改后的代码（我尝试删除cookie并保留所有内容，无所谓）：

def get_asins_in_page(soup, sponsored):
    asins_dict = {}
    asins_sponsored_dict = {}
    reslist = soup.find("ul", {"id": "s-results-list-atf"})
    for r in reslist.find_all('li'):
        print r.findAll('h5')
        asins_dict[r.get('data-asin')] = r.get('id')
    return asins_dict

def find_ranking_by_asin(keyword, target_asin, sponsored):
    print "%s %s"%(keyword, target_asin)
    loop_count = 0
    headers = {
            'Accept' : 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
            'Accept-Encoding' : 'gzip, deflate, sdch',
            'Accept-Language' : 'en-US,en;q=0.8,ar;q=0.6',
            'Cache-Control' : 'max-age=0',
            'Connection' : 'keep-alive',
            'Cookie' : """x-wl-uid=1sKNa/Tu+dnJiObdvPzWmOWvHoQHs7SbunE2P1wtUNyXZoFmxflkD74oIUtjg6je4M1DNJgid9D73eSQ/1szSzyViGKhQNfYhzyrIF+0sYuCypgc4oFkknUPA4xZ0Aeienl0XdGyC/GE=; bhqns=d0sdm59meaki4gsmq4gsdpv5k3; x-main="HSxQRguP7RaA0XNnOlvYoSu?jhNN?Gbu"; b2b-main=0; s_vnum=1857890451251%26vn%3D3; appstore-devportal-locale=en_US; aws_lang=en; aws-target-data=%7B%22support%22%3A%221%22%7D; s_dslv=1428249404729; aws-target-visitor-id=1428249404407-552911.26_29; s_sq=%5B%5BB%5D%5D; _mkto_trk=id':'810-GRW-452&token':'_mch-amazon.com-1428249580944-19910; __utma=194891197.1337326270.1428250257.1428250257.1428250257.1; __utmc=194891197; __utmz=194891197.1428250257.1.1.utmccn=(referral)|utmcsr=google.com.eg|utmcct=/|utmcmd=referral; pN=1; s_pers=%20s_fid%3D3E166C526619A613-1D8EA49490B2AAB8%7C1491407981003%3B%20s_dl%3D1%7C1428251381006%3B%20gpv_page%3DUS%253AAS%253APADS-how-it-works%7C1428251381011%3B%20s_ev15%3D%255B%255B%2527NSGoogle%2527%252C%25271428249581020%2527%255D%255D%7C1586102381020%3B%20s_invisit%3Dtrue%7C1428252056959%3B%20s_nr%3D1428250256962-Repeat%7C1436026256962%3B; s_sess=%20c_m%3Dwww.google.com.egNatural%2520Search%3B%20s_ppvl%3DUS%25253AAS%25253APADS-how-it-works%252C56%252C56%252C955%252C1920%252C955%252C1920%252C1080%252C1%252CL%3B%20s_cc%3Dtrue%3B%20s_sq%3D%3B%20s_ppv%3DUS%25253AAS%25253APADS-how-it-works%252C91%252C56%252C1555%252C1920%252C955%252C1920%252C1080%252C1%252CL%3B; session-token=opZ2DsH3n42Pz4spSbxaz9oQx5kGTKq1pj4n5WE+pGWvRBk6IyjvUQWw/GrDH2dGqbwR7d97ibcno5K4B1yUnpoVceB8aEDziGrWpU+I+tHBkWWy0ZMorJZowa3DMS40gfMTAc1Gd/o4ZpYOibC1SPQEzU3Eg2OslDRNyys+e90lJaothbV12MO62XiHFsnjjhCVFk8Ztr3hRgnl5oC1NvbZ9lZ7QjmhDP9wXgnYmG6wevsgqdukBbKoohHv1kGOWg60CWLBFS/RhVqukMAO5g==; skin=noskin; ubid-main=182-4576256-0011665; session-id-time=2082787201l; session-id=180-4378028-6113727; csm-hit=1RPD28BQJKGVJNHSZKFR+s-1RPD28BQJKGVJNHSZKFR|1428854614288""",
            'Host' : 'www.amazon.com',
            'User-Agent' : 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2272.118 Safari/537a'
            } 
    url = "http://www.amazon.com/s/?url=search-alias%3Daps&field-keywords="+urllib.quote(keyword)
    while True:
        loop_count+=1
        r = requests.get(url, headers = headers)
        data = r.text
        soup = BeautifulSoup(data)
        url ="http://www.amazon.com" + soup.find("a",{"id":"pagnNextLink"}).get('href') #next_page_url 
        asins_dict = get_asins_in_page(soup, False)
        if target_asin in asins_dict:
            return asins_dict[target_asin].replace("result_","")

        #fail-safe:
        if loop_count > 50: return -1

来自beautifulsoup的amazon scraping与使用浏览器不同

0 个答案: