BeautifulSoup - 在多个页面上抓取 html 表格

Question

I'm newbie on Python and BeautifulSoup, I would like to scrape multiple pages in csv but when I'm trying to store those 3 links only the last one it's stored in csv.

How can I fix my issue ?

## importing bs4, requests, fake_useragent and csv modules
from bs4 import BeautifulSoup
import requests
from fake_useragent import UserAgent
import csv

## create an array with URLs
urls = [
'https://www.scansante.fr/applications/casemix_ghm_cmd/submit?snatnav=&typrgp=etab&annee=2019&type=ghm&base=0&typreg=noreg2016&noreg=99&finess=750300360&editable_length=10',
'https://www.scansante.fr/applications/casemix_ghm_cmd/submit?snatnav=&typrgp=etab&annee=2019&type=ghm&base=0&typreg=noreg2016&noreg=99&finess=030780118&editable_length=10',
'https://www.scansante.fr/applications/casemix_ghm_cmd/submit?snatnav=&typrgp=etab&annee=2019&type=ghm&base=0&typreg=noreg2016&noreg=99&finess=620103432&editable_length=10'
]

## initializing the UserAgent object
user_agent = UserAgent()

## starting the loop
for url in urls:
    ## getting the reponse from the page using get method of requests module
    page = requests.get(url, headers={"user-agent": user_agent.chrome})

    ## storing the content of the page in a variable
    html = page.content

    ## creating BeautifulSoup object
    soup = BeautifulSoup(html, "html.parser")
    table = soup.findAll("table", {"class":"table"})[0]
    rows = table.findAll("tr")

with open("test.csv", "wt+", newline="") as f:
    writer = csv.writer(f)
    for row in rows:
        csv_row = []
        for cell in row.findAll(["td", "th"]):
            csv_row.append(cell.get_text())
        writer.writerow(csv_row)

Thanks a lot !

Answer 1

To simplify the reading process of the rows, you could also give a shot with pandas :

import csv
import requests
from bs4 import BeautifulSoup
import pandas as pd


urls = [
'https://www.scansante.fr/applications/casemix_ghm_cmd/submit?snatnav=&typrgp=etab&annee=2019&type=ghm&base=0&typreg=noreg2016&noreg=99&finess=750300360&editable_length=10',
'https://www.scansante.fr/applications/casemix_ghm_cmd/submit?snatnav=&typrgp=etab&annee=2019&type=ghm&base=0&typreg=noreg2016&noreg=99&finess=030780118&editable_length=10',
'https://www.scansante.fr/applications/casemix_ghm_cmd/submit?snatnav=&typrgp=etab&annee=2019&type=ghm&base=0&typreg=noreg2016&noreg=99&finess=620103432&editable_length=10'
]

headers = {'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:77.0) Gecko/20100101 Firefox/77.0'}

all_data = []
for url in urls:
    page = requests.get(url, headers=headers)

    soup = BeautifulSoup(page.content, "html.parser")
    table = soup.findAll("table", {"class":"table"})[0]
    
    df_table = pd.read_html(str(table))[0]
    
    #add a column with additional info
    df_table['hit'] = soup.find("span", {"class":"c"}).text.strip() 
    
    #store the table in a list of tables
    all_data.append(df_table)

#concat the tables and export them to csv
pd.concat(all_data).to_csv('test.csv',index=False)

Answer 2

In your code, you don't store rows variable to anywhere, so you write only values from your last URL to CSV file. This example will write values from all three URLs:

import csv
import requests
from bs4 import BeautifulSoup


urls = [
'https://www.scansante.fr/applications/casemix_ghm_cmd/submit?snatnav=&typrgp=etab&annee=2019&type=ghm&base=0&typreg=noreg2016&noreg=99&finess=750300360&editable_length=10',
'https://www.scansante.fr/applications/casemix_ghm_cmd/submit?snatnav=&typrgp=etab&annee=2019&type=ghm&base=0&typreg=noreg2016&noreg=99&finess=030780118&editable_length=10',
'https://www.scansante.fr/applications/casemix_ghm_cmd/submit?snatnav=&typrgp=etab&annee=2019&type=ghm&base=0&typreg=noreg2016&noreg=99&finess=620103432&editable_length=10'
]

headers = {'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:77.0) Gecko/20100101 Firefox/77.0'}

all_data = []
for url in urls:
    page = requests.get(url, headers=headers)

    soup = BeautifulSoup(page.content, "html.parser")
    table = soup.findAll("table", {"class":"table"})[0]

    # here I store all rows to list `all_data`
    for row in table.findAll('tr'):
        tds = [cell.get_text(strip=True, separator=' ') for cell in row.findAll(["td", "th"])]
        all_data.append(tds)
        print(*tds)

# write list `all_data` to CSV
with open("test.csv", "wt+", newline="") as f:
    writer = csv.writer(f)
    for row in all_data:
        writer.writerow(row)

Writes test.csv from all three URLs (screenshot from LibreOffice):