问题

以下是代码部分，不需要翻译：

import requests
from bs4 import BeautifulSoup

def get_contact_person_and_fax_number(url):
    # 发送GET请求到链接url
    link_response = requests.get(url)

    # 使用BeautifulSoup解析HTML内容
    link_soup = BeautifulSoup(link_response.content, "html.parser")

    # 查找联系人和传真号码
    contact_person = None
    fax_number = None
    contact_div = link_soup.find("div", {"class": "info-gen-box clearfix"})
    if contact_div:
        contact_person = contact_div.find("div", {"class": "info-gen-box clearfix"})
        if contact_person:
            contact_person = contact_person.text.strip()
        fax_number = contact_div.find("div", {"class": "info-fax info-mar"})
        if fax_number:
            fax_number = fax_number.text.strip()

    return (contact_person, fax_number)

# 提示用户输入NAICS代码
naics_code = input("输入NAICS代码: ")

# 遍历所有搜索结果页面
for page_num in range(1, 81):
    # 发送GET请求到搜索页面
    page_url = f"https://www.usaopps.com/government_contractors/search.htm?naics={naics_code}&page={page_num}"
    page_response = requests.get(page_url)

    # 使用BeautifulSoup解析HTML内容
    page_soup = BeautifulSoup(page_response.content, "html.parser")

    # 查找当前页面上的所有搜索结果
    results = page_soup.select(".lr-title")
    links = page_soup.find_all('div', {'class': 'lr-title'})

    # 遍历每个搜索结果链接并提取联系人和传真号码（如果可用）
    for link in links:
        # 提取链接URL
        url = link.find('a').get('href')

        if not url.startswith('http'):
            url = f"https://www.usaopps.com{url}"

        # 获取此链接的联系人和传真号码
        contact_person, fax_number = get_contact_person_and_fax_number(url)

        # 打印结果
        print(f"Contact Person: {contact_person}")
        print(f"Fax Number: {fax_number}")

如果您需要任何进一步的翻译或帮助，请告诉我。

import requests
from bs4 import BeautifulSoup


def get_contact_person_and_fax_number(url):
    # Send GET request to link url
    link_response = requests.get(url)

    # Parse HTML content with BeautifulSoup
    link_soup = BeautifulSoup(link_response.content, "html.parser")

    # Find the contact person and fax number
    contact_person = None
    fax_number = None
    contact_div = link_soup.find("div", {"class": "info-gen-box clearfix"})
    if contact_div:
        contact_person = contact_div.find("div", {"class": "info-gen-box clearfix"})
        if contact_person:
            contact_person = contact_person.text.strip()
        fax_number = contact_div.find("div", {"class": "info-fax info-mar"})
        if fax_number:
            fax_number = fax_number.text.strip()

    return (contact_person, fax_number)


# Prompt user for NAICS code
naics_code = input("Enter NAICS code: ")

# Loop through all search result pages
for page_num in range(1, 81):
    # Send GET request to search page
    page_url = f"https://www.usaopps.com/government_contractors/search.htm?naics={naics_code}&page={page_num}"
    page_response = requests.get(page_url)

    # Parse HTML content with BeautifulSoup
    page_soup = BeautifulSoup(page_response.content, "html.parser")

    # Find all search results on current page
    results = page_soup.select(".lr-title")
    links = page_soup.find_all('div', {'class': 'lr-title'})

    # Loop through each search result link and extract contact person and fax number if available
    for link in links:
        # Extract link url
        url = link.find('a').get('href')

        if not url.startswith('http'):
            url = f"https://www.usaopps.com{url}"

        # Get contact person and fax number for this link
        contact_person, fax_number = get_contact_person_and_fax_number(url)

        # Print results
        print(f"Contact Person: {contact_person}")
        print(f"Fax Number: {fax_number}")

答案1

得分: 1

这个部分对我来说似乎是问题所在。一旦contact_div被设置，就再也没有相同类别的div存在...实际上，看网站的情况，它的设置不再是这样的了。自从您开始这个项目以来，它有变化吗？

contact_div = link_soup.find("div", {"class": "info-gen-box clearfix"})
if contact_div:
    contact_person = contact_div.find("div", {"class": "info-gen-box clearfix"})
    if contact_person:
        contact_person = contact_person.text.strip()
    fax_number = contact_div.find("div", {"class": "info-fax info-mar"})
    if fax_number:
        fax_number = fax_number.text.strip()

我只看到一个<div class="info-gen-box clearfix">，而它在您尝试访问它内部的info-fax info-mar div之前就已经关闭了。

contact_div = link_soup.find("div", {"class": "info-gen-box clearfix"})
if contact_div:
contact_person = contact_div.find("div", {"class": "info-gen-box clearfix"})
if contact_person:
contact_person = contact_person.text.strip()
fax_number = contact_div.find("div", {"class": "info-fax info-mar"})
if fax_number:
fax_number = fax_number.text.strip()

答案2

得分: 0

以下是翻译的代码部分：

### 缺失信息背后的原因

在 `get_contact_person_and_fax_number` 中，你有以下代码：

```py
contact_div = link_soup.find("div", {"class": "info-gen-box clearfix"})
if contact_div:
    contact_person = contact_div.find("div", {"class": "info-gen-box clearfix"})

fax_number = contact_div.find("div", {"class": "info-fax info-mar"})

然而，在这些页面上没有嵌套的 div.info-gen-box.clearfix（这是一个打字错误吗？）和 div.info-fax.info-mar 不在 contact_div 内（你可以将 fax_number=link_soup.find("div",{"class":"info-fax info-mar"}) 放在 if contact_div 之外）。

建议的解决方案

以下是我建议的 get_contact_person_and_fax_number 的版本：

def get_company_info(compUrl, pre_print=''):
    # 使用 requests + BeautifulSoup 获取并解析 HTML 内容
    lSoup = BeautifulSoup((lr := requests.get(compUrl)).content, "html.parser")

    # 查找侧边框，并将 dt/dd 标签与公司信息一起合并
    contact_div = lSoup.select_one('div[id="box-sideinfo"] dl:has(dt+dd)')
    ckv = zip(
        contact_div.select('dt:has(+dd)'), contact_div.select('dt+dd')
    ) if contact_div else []  # 如果找不到容器则使用空列表
    # 从 zip 中构建字典
    get_k = lambda dx: ' '.join(dx.get_text(' ').split()).strip(':')  # [最小间距]
    def get_v(dx):
        if dx.find('dd'): return list(dx.stripped_strings)[0]  # 用于嵌套信息
        return dx.get_text(' • ', strip=True)
    company_dets = {get_k(dt): get_v(dd) for dt, dd in ckv}  # [字典解析]
    # 打印并返回
    lrStat = f'<[{lr.status_code} {lr.reason}]> 在 {lr.elapsed} 从 {lr.url}'
    if isinstance(pre_print, str):
        print(pre_print + f'{len(company_dets)} 家公司详细信息 - {lrStat}')
    if not contact_div: company_dets['错误消息'] = f'无信息 - {lrStat}'
    return company_dets if company_dets else {'msg': f'！错误！无信息 - {lrStat}'}

def get_contact_person_and_fax_number(url):
    cDets = get_company_info(url, None)
    return (cDets.get('联系人'), cDets.get('传真'))

你也可以直接在 for link in links: 中使用 get_company_info：

# 如果不是以 'http' 开头的URL，添加前缀
if not url.startswith('http'):
    url = f"https://www.usaopps.com{url}"
# 打印此链接的联系人和传真号码
keys_list, company_info = ['联系人', '传真'], get_company_info(url)  #, None)
for k in keys_list:
    print(f'    {k}: {company_info.get(k)}')

其他建议

以下建议不是必需的，但我有关于你的 for page_num... 循环的一些建议/备注：

• 我认为更安全的方式是这样的：

      for link in page_soup.select('div.lr-title:has(a[href])'):
          url = link.find('a', href=True)['href']
  

  • [顺便问一下，为什么你有 results 和 links，我预计它们是相同的 ResultSet，特别是因为你似乎没有使用 results ？]
• 应该有一些方式来停止循环，以防止不必要地发送请求到没有结果的页面；可以
  • 只需 if not links: break 来停在第一个没有结果的页面
  • 或者使用一个具有两个条件的 while 循环 [下面进行了演示]

# 提示用户输入 NAICS 代码并构建第一页的URL
naics_code = input("输入NAICS代码：")
page_url = f"https://www.usaopps.com/government_contractors/search.htm?naics={naics_code}"

# 开始 while 循环
all_rows, pg_num, max_pgs = [], 0, 81
# max_pgs = int(max_pgs) if (max_pgs:=input('Page limit:')).isdigit() else None
while page_url and (pg_num := pg_num + 1) <= (max_pgs if max_pgs else pg_num):
    if not page_url.startswith('http'): page_url = f"https://www.usaopps.com{page_url}"
    pgSoup = BeautifulSoup((pr := requests.get(page_url)).content, "html.parser")
    llen = len(links := pgSoup.select('div.lr-title:has(a[href])'))

    ## 仅用于打印进度（结果数量和哪一页）
    abtRes = pgSoup.select('div.list-total,div.list-head>h2')[:2]
    pgProgressPlus = ' for '.join(
)
    print(f'[Page {pg_num}][{llen} 链接]', pgProgressPlus, '\n')

    # 遍历并抓取结果链接，同时打印和/或收集公司信息
    for ln, link in enumerate(links, 1):
        url = link.find('a', href=True)['href']
        if not url.startswith('http'): url = f"https://www.usaopps.com{url}"
        # all_rows.append(company_info:=get_company_info(url,None)) ## 收集数据
        company_info = get_company_info(url, f'\n  [Page {pg_num}][Link {ln} of {llen}]')
        # for k,v in company_info.items():print(f'      {k}: {v}') ## 打印所有
        keys_list = ['联系人', '传真']
        for k in keys_list: print(f'      {k}: {company_info.get(k)}')

    # 找到下一页链接并更新为下一个循环
    next_link = pgSoup.select_one('span.page-link a[href]:-soup-contains("下一页")')
    page_url = next_link['

<details>
<summary>英文:</summary>

### Reason Behind the Missing Information

In `get_contact_person_and_fax_number` you have

&gt; ```py
&gt;     contact_div = link_soup.find(&quot;div&quot;, {&quot;class&quot;: &quot;info-gen-box clearfix&quot;})
&gt;     if contact_div:
&gt;         contact_person = contact_div.find(&quot;div&quot;, {&quot;class&quot;: &quot;info-gen-box clearfix&quot;})
&gt; ```
&gt; ```py
&gt;         fax_number = contact_div.find(&quot;div&quot;, {&quot;class&quot;: &quot;info-fax info-mar&quot;})
&gt; ```

However, there is no nested `div.info-gen-box.clearfix`&lt;sup&gt;([view][1])&lt;/sup&gt; on these pages (was that a typo?) and `div.info-fax.info-mar`&lt;sup&gt;([view][2])&lt;/sup&gt; is not inside *`contact_div`* (you could just have `fax_number=link_soup.find(&quot;div&quot;,{&quot;class&quot;:&quot;info-fax info-mar&quot;})` **outside** the *`if contact_div`* block).

---

### Suggested Solution

Below is my suggested version of `get_contact_person_and_fax_number`&lt;sup&gt;([view example output][3])&lt;/sup&gt;

```py
def get_company_info(compUrl, pre_print=&#39;&#39;):
    # Fetch and Parse HTML content with requests + BeautifulSoup
    lSoup = BeautifulSoup((lr:=requests.get(compUrl)).content, &quot;html.parser&quot;)

    # Find the side box and zip together dt/dd tags with company info
    contact_div = lSoup.select_one(&#39;div[id=&quot;box-sideinfo&quot;] dl:has(dt+dd)&#39;) 
    ckv = zip(
        contact_div.select(&#39;dt:has(+dd)&#39;), contact_div.select(&#39;dt+dd&#39;)
    ) if contact_div else [] ## use empty list if container is not found 
    
    # Build a dictionary from zip
    get_k = lambda dx: &#39; &#39;.join(dx.get_text(&#39; &#39;).split()).strip(&#39;:&#39;) ## [minimal spacing]
    def get_v(dx):
        if dx.find(&#39;dd&#39;): return list(dx.stripped_strings)[0] ## for nested info
        return dx.get_text(&#39; • &#39;, strip=True)
    company_dets = {get_k(dt): get_v(dd) for dt,dd in ckv} ## [dict comprehension]

    # Print and Return
    lrStat = f&#39;&lt;[{lr.status_code} {lr.reason}]&gt; in {lr.elapsed} from {lr.url}&#39;
    if isinstance(pre_print, str):
        print(pre_print + f&#39;{len(company_dets)} company details - {lrStat}&#39;)
    if not contact_div: company_dets[&#39;Error Message&#39;] = f&#39;No info - {lrStat}&#39;
    return company_dets if company_dets else {&#39;msg&#39;: f&#39;!Error! No info - {lrStat}&#39;}

def get_contact_person_and_fax_number(url):
    cDets = get_company_info(url, None)
    return (cDets.get(&#39;Contact Person&#39;), cDets.get(&#39;Fax&#39;))

You could also directly use get_company_info in for link in links:^{(view example output)}

        # if not url.startswith('http'): url = f"https://www.usaopps.com{url}"

        # Print contact person and fax number for this link
        keys_list, company_info = ['Contact Person', 'Fax'], get_company_info(url) #, None)
        for k in keys_list: print(f'    {k}: {company_info.get(k)}')

Other Suggestions

These are not essential, but I have some recommendations/notes about your for page_num... loop:

• imo it would be safer to have

      for link in page_soup.select('div.lr-title:has(a[href])'):
          url = link.find('a', href=True)['href']
  

  • [btw, why do you have results and links, which I expect are the same ResultSet, especially since you don't see to be using results for anything?]
• there should be something to stop the loop after the last page, otherwise you could be unnecessarily sending requests to pages without results; either
  • just if not links: break to stop as soon as you get to a page without results
  • or use a while loop with two conditions [demonstrated below]

# Prompt user for NAICS code and build page 1 URL
naics_code = input("Enter NAICS code: ")
page_url = f"https://www.usaopps.com/government_contractors/search.htm?naics={naics_code}"

# Begin while loop
all_rows, pg_num, max_pgs = [], 0, 81
# max_pgs = int(max_pgs) if (max_pgs:=input('Page limit:')).isdigit() else None
while page_url and (pg_num:=pg_num+1)<=(max_pgs if max_pgs else pg_num):
    if not page_url.startswith('http'): page_url = f"https://www.usaopps.com{page_url}"
    pgSoup = BeautifulSoup((pr:=requests.get(page_url)).content, "html.parser")
    llen = len(links := pgSoup.select('div.lr-title:has(a[href])'))

    ## JUST FOR PRINTING PROGRESS (how many results and which page)
    abtRes = pgSoup.select('div.list-total,div.list-head>h2')[:2]
    pgProgressPlus = ' for '.join(
)
    print(f'[Page {pg_num}][{llen} Links]', pgProgressPlus, '\n')

    # Loop through and scrape result links while printing and/or collecting company info
    for ln, link in enumerate(links,1):
        url = link.find('a', href=True)['href']
        if not url.startswith('http'): url = f"https://www.usaopps.com{url}"

        # all_rows.append(company_info:=get_company_info(url,None)) ## collect data
        company_info = get_company_info(url, f'\n  [Page {pg_num}][Link {ln} of {llen}]')
        
        # for k,v in company_info.items():print(f'      {k}: {v}') ## print all
        keys_list = ['Contact Person','Fax']
        for k in keys_list: print(f'      {k}: {company_info.get(k)}')
    
    # Find next page link and update for next loop
    next_link = pgSoup.select_one('span.page-link a[href]:-soup-contains("Next")')
    page_url = next_link['href'] if next_link else None
    print('\n\n')

If you uncomment the ## collect data line, the collected data would be something like