如何使用Beautiful Soup4从Twitter用户资料中获取位置？

Question

所以，我想从一个给定的Twitter账户的简介中获取位置信息。

handles = ['IndieWire' , 'AFP', 'UN']

for x in handles:
    url= "https://twitter.com/" + x
    try:
        html = req.get(url)
    except Exception as e:
        print(f"Failed to fetch page for url {url} due to: {e}")
        continue
    soup = BeautifulSoup(html.text,'html.parser')
    try:
        label = soup.find('span',{'class':"ProfileHeaderCard-locationText"})
        label_formatted = label.string.lstrip()
        label_formatted = label_formatted.rstrip()
        if label_formatted != "":
            location_list.append(label_formatted)
            print(x + ' : ' + label_formatted)
        else:
            location_list.append(label_formatted)
            print(x + ' : ' + 'Not found')
    except AttributeError:
        try:
            label2 = soup.findAll('span',{"class":"ProfileHeaderCard-locationText"})[0].get_text()
            label2 = str(label2)
            label2_formatted = label2.lstrip()
            label2_formatted = label2_formatted.rstrip()
            location_list.append(label_formatted)
            print(x + ' : ' + label2_formatted)
        except:
            print(x + ' : ' + 'Not found')
    except:
            print(x + ' : ' + 'Not found')

这段代码在几个月前我用的时候还能用。我改变了一点，现在检查Twitter页面的源头后，但我仍然无法得到的位置。希望你能帮助

Answer 1

使用手机版Twitter获取位置。

比如说。

import requests
from bs4 import BeautifulSoup


handles = ['IndieWire' , 'AFP', 'UN']

ref = 'https://twitter.com/{h}'
headers = {'Referer': '',}
url = 'https://mobile.twitter.com/i/nojs_router?path=/{h}'

for h in handles:
    headers['Referer'] = ref.format(h=h)
    soup = BeautifulSoup( requests.post(url.format(h=h), headers=headers).content, 'html.parser' )
    loc = soup.select_one('.location')
    if loc:
        print(h, loc.text)
    else:
        print(h, 'Not Found')

Prints:

IndieWire New York, NY
AFP France
UN New York, NY