为公司报废年度报告

Question

我正在从网站上提取年度报告 pdf 文件。

import requests
import pandas as pd 
from bs4 import BeautifulSoup 
url1 = "https://investor.alaskaair.com/financial-information/sec-filings?field_nir_sec_form_group_target_id%5B%5D=471&field_nir_sec_date_filed_value=#views-exposed-form-widget-sec-filings-table"
source = requests.get(url1)
soup = BeautifulSoup(source.text , "html.parser")

我正在尝试从上面提到的 URL 中提取列，但在视图列中我们只有 8 行，因此抛出值错误 = 数组的长度必须相同

<div class="snippet" data-lang="js" data-hide="false" data-console="true" data-babel="false">
<div class="snippet-code">
<pre><code>tag2 = soup.find_all('div' , class_="field field--name-field-nir-sec-form-group field--type-entity-reference field--label-inline field__item")
def filing_group(tag2):
    filing_group = []
    for i in tag2:
        filing_group.append(i.text.strip())
    return filing_group
filing_group(tag2) 

tag4 = soup.find_all('span' , class_ = "file file--mime-application-pdf file--application-pdf")
def view(tag4):
    view = []
    try: 
        for i in tag4:
            view.append(i.a.get('href'))
    except AttributeError:
        view.append(None)
    return view
view(tag4)

def scrape_page():
    all_info = {}
    all_info = {
        "Filing Group" : [],
        "View" : []
    }
    all_info["Filing Group"] += filing_group(tag2) 
    all_info["View"] += view(tag4)
    
    return all_info
scrape_page_df = pd.DataFrame(scrape_page())

Answer 1

正如@hteza 所建议的，缺少链接，因此您需要逐行而不是逐列构建数据：

table = soup.find('table', {'class': 'views-table'})
data = []
for row in table.find('tbody').find_all('tr'):
    group = row.find('div', {'class': 'field field--name-field-nir-sec-form-group field--type-entity-reference field--label-inline field__item'}).text
    pdf = row.find('span', {'class': 'file file--mime-application-pdf file--application-pdf'})
    view = pdf.find('a')['href'] if pdf else None
    data.append({'Filling Group': group, 'View': view})

df = pd.DataFrame(data)

输出：

>>> df
    Filling Group                                                                              View
0  Annual Filings  https://investor.alaskaair.com/static-files/a686b1d8-6bc5-41ee-9e1a-3860907ed26f
1  Annual Filings  https://investor.alaskaair.com/static-files/33d26e56-06c0-44bc-8078-58fbd8103186
2  Annual Filings  https://investor.alaskaair.com/static-files/16b87b83-b3bf-4e33-8ef5-148cf48b336b
3  Annual Filings  https://investor.alaskaair.com/static-files/5e3082dd-f9fe-493e-9bf9-978c658a13a4
4  Annual Filings  https://investor.alaskaair.com/static-files/086708d7-3a13-4683-a381-21eb77634172
5  Annual Filings  https://investor.alaskaair.com/static-files/a09bc200-0c2b-478c-8827-d84044c1fcba
6  Annual Filings  https://investor.alaskaair.com/static-files/66234ad1-4934-4330-8770-36c4ccebebd0
7  Annual Filings                                                                              None
8  Annual Filings  https://investor.alaskaair.com/static-files/78aa7028-887b-41e8-a173-bf27dccb34b0
9  Annual Filings                                                                              None

Answer 2

使用：

table = soup.find('table', {'class':"nirtable views-table views-view-table cols-5 collapse-table-wide"})
trs = [x.find_all('td') for x in table.find_all('tr')]
vs = []
ls = []
for tr in trs:
    if len(tr)>0:
        v = 'https://investor.alaskaair.com/'+tr[1].a['href']
        print(v)
        try:
            l = tr[4].find('span', {'class':'file file--mime-application-pdf file--application-pdf'}).a.get('href')
        except:
            l = None
        print(l)
        vs.append(v)
        ls.append(l)
pd.DataFrame({'v':vs, 'l':ls})

输出：