python解析网页中的table表格并下载为csv代码-python代码-BFW代码库

python解析网页中的table表格并下载为csv代码

代码语言：python

所属分类：web系统

代码描述：python解析网页中的table表格并下载为csv代码

下面为部分代码预览，完整代码请点击下载或在bfwstudio webide中打开

#!/usr/local/python3/bin/python3
# -*- coding: utf-8 -*
import requests
import pandas as pd
from bs4 import BeautifulSoup as bs

USER_AGENT = "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.157 Safari/537.36"
# US english
LANGUAGE = "en-US,en;q=0.5"

def get_soup(url):
    """Constructs and returns a soup using the HTML content of `url` passed"""
    # initialize a session
    session = requests.Session()
    # set the User-Agent as a regular browser
    session.headers['User-Agent'] = USER_AGENT
    # request for english content (optional)
    session.headers['Accept-Language'] = LANGUAGE
    session.headers['Content-Language'] = LANGUAGE
    # make the request
    html = session.get(url)
    # return the soup
    return bs(html.content, "html.parser")


def get_all_tables(soup):
    """Extracts and returns all tables in a soup object"""
    return soup.find_all("table")


def get_table_headers(table):
    """Given a table soup, returns all the headers"""
    headers = []
    for th in table.find("tr").find_all("th"):
        headers.append(th.text.strip())
    return headers


def get_table_rows(table):
    """Given a table, returns all its rows"""
    rows = []
    for tr in table.find_all("tr")[1:]:
        cells = []
        # grab all td tags in this table row
        tds = tr.find_all("td")
        if len(tds) == 0:
            # i.........完整代码请登录后点击上方下载按钮下载查看