分页不遍历页面
Pagination not iterating over pages
想要遍历此 url ""url = "https://www.iata.org/en/about/members/airline-list/"" 中的所有页面并将结果转储到.csv 文件。
如何将实现一段代码来遍历页面包含在下面的当前代码中?
import requests
import pandas as pd
from bs4 import BeautifulSoup
from urllib.request import Request
url = 'https://www.iata.org/en/about/members/airline-list/'
req = Request(url , headers = {
'accept':'*/*',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.190 Safari/537.36'})
data = []
while True:
print(url)
html = requests.get(url)
soup = BeautifulSoup(html.text, 'html.parser')
data.append(pd.read_html(soup.select_one('table.datatable').prettify())[0])
if soup.select_one('span.pagination-link.is-active + div a[href]'):
url = soup.select_one('span.pagination-link.is-active + div a')['href']
else:
break
df = pd.concat(data)
df.to_csv('airline-list.csv',encoding='utf-8-sig',index=False)
试试这个方法:
for i in range(1, 30):
url = f'https://www.iata.org/en/about/members/airline-list/?page={i}&search=&ordering=Alphabetical'
html = requests.get(url)
soup = BeautifulSoup(html.text, 'html.parser')
data.append(pd.read_html(soup.select_one('table.datatable').prettify())[0])
要动态获取数据,请使用:
import pandas as pd
import requests
import bs4
url = 'https://www.iata.org/en/about/members/airline-list/?page={page}&search=&ordering=Alphabetical'
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.190 Safari/537.36'}
# Total number of pages
html = requests.get(url.format(page=1), headers=headers)
soup = bs4.BeautifulSoup(html.text)
pages = int(soup.find_all('a', {'class': 'pagination-link'})[-2].text)
data = []
for page in range(1, pages+1):
html = requests.get(url.format(page=page, headers=headers))
data.append(pd.read_html(html.text)[0])
df = pd.concat(data)
输出:
>>> df
Airline Name IATA Designator 3 digit code ICAO code Country / Territory
0 ABX Air GB 832 ABX United States
1 Aegean Airlines A3 390 AEE Greece
2 Aer Lingus EI 53 EIN Ireland
3 Aero Republica P5 845 RPB Colombia
4 Aeroflot SU 555 AFL Russian Federation
.. ... ... ... ... ...
3 WestJet WS 838 WJA Canada
4 White coloured by you WI 97 WHT Portugal
5 Wideroe WF 701 WIF Norway
6 Xiamen Airlines MF 731 CXA China (People's Republic of)
7 YTO Cargo Airlines YG 860 HYT China (People's Republic of)
[288 rows x 5 columns]
想要遍历此 url ""url = "https://www.iata.org/en/about/members/airline-list/"" 中的所有页面并将结果转储到.csv 文件。
如何将实现一段代码来遍历页面包含在下面的当前代码中?
import requests
import pandas as pd
from bs4 import BeautifulSoup
from urllib.request import Request
url = 'https://www.iata.org/en/about/members/airline-list/'
req = Request(url , headers = {
'accept':'*/*',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.190 Safari/537.36'})
data = []
while True:
print(url)
html = requests.get(url)
soup = BeautifulSoup(html.text, 'html.parser')
data.append(pd.read_html(soup.select_one('table.datatable').prettify())[0])
if soup.select_one('span.pagination-link.is-active + div a[href]'):
url = soup.select_one('span.pagination-link.is-active + div a')['href']
else:
break
df = pd.concat(data)
df.to_csv('airline-list.csv',encoding='utf-8-sig',index=False)
试试这个方法:
for i in range(1, 30):
url = f'https://www.iata.org/en/about/members/airline-list/?page={i}&search=&ordering=Alphabetical'
html = requests.get(url)
soup = BeautifulSoup(html.text, 'html.parser')
data.append(pd.read_html(soup.select_one('table.datatable').prettify())[0])
要动态获取数据,请使用:
import pandas as pd
import requests
import bs4
url = 'https://www.iata.org/en/about/members/airline-list/?page={page}&search=&ordering=Alphabetical'
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.190 Safari/537.36'}
# Total number of pages
html = requests.get(url.format(page=1), headers=headers)
soup = bs4.BeautifulSoup(html.text)
pages = int(soup.find_all('a', {'class': 'pagination-link'})[-2].text)
data = []
for page in range(1, pages+1):
html = requests.get(url.format(page=page, headers=headers))
data.append(pd.read_html(html.text)[0])
df = pd.concat(data)
输出:
>>> df
Airline Name IATA Designator 3 digit code ICAO code Country / Territory
0 ABX Air GB 832 ABX United States
1 Aegean Airlines A3 390 AEE Greece
2 Aer Lingus EI 53 EIN Ireland
3 Aero Republica P5 845 RPB Colombia
4 Aeroflot SU 555 AFL Russian Federation
.. ... ... ... ... ...
3 WestJet WS 838 WJA Canada
4 White coloured by you WI 97 WHT Portugal
5 Wideroe WF 701 WIF Norway
6 Xiamen Airlines MF 731 CXA China (People's Republic of)
7 YTO Cargo Airlines YG 860 HYT China (People's Republic of)
[288 rows x 5 columns]