Google検索結果ページをスクレイピング【Python x BeautifulSoup】

import urllib.request
from bs4 import BeautifulSoup

url = "https://101010.fun/posts/world-ios-android-share-2021.html"
req = urllib.request.Request(url)

with urllib.request.urlopen(req) as res:
    html = res.read()
    soup = BeautifulSoup(html, 'html.parser')
    title = soup.find('title').get_text()
    print(title)

soup = BeautifulSoup(html, 'html.parser')

for a_tag in soup.find_all('a'):
    h2 = a_tag.select("h2")
    if len(h2) > 0:
        print(h2.get_text())

for a in soup.find_all('a'):
    href = a.get('href')

soup.find_all("a", class_="hoge")

parent = h2.parent
print(parent.get_text())

next_sibling = h2.next_sibling
print(next_sibling.get_text())

previous_sibling = h2.previous_sibling
print(previous_sibling.get_text())

soup = BeautifulSoup("<a>Hoge</a>")
soup.a.append("Fuga")

# Created by Toshihiko Arai.
# https://101010.fun/programming/python-beautifulsoup-googlerank.html

import urllib.request
from urllib.parse import quote
from bs4 import BeautifulSoup
import time

keyword = 'ios android シェア'
target = 'https://101010.fun/posts/world-ios-android-share-part1.html'
user_agent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.111 Safari/537.36"

def get_search_html(keyword, page):
    start = "&start=" + str(page * 10) # 次ページstart=10
    url = 'https://www.google.com/search?q=' + quote(keyword) + start 
    
    headers = {'User-Agent': user_agent}
    req = urllib.request.Request(url, headers=headers)

    with urllib.request.urlopen(req) as res:
        body = res.read()
        return body

def get_page_rank(soup, page):
    res_rank = 1

    for a_tag in soup.find_all('a'):
        h3_tag = a_tag.select("h3")

        if len(h3_tag) > 0:
            if a_tag.get('href').startswith(target) == True:
                # print(h3_tag[0].get_text())
                # print(a_tag.get('href'))
                return res_rank + page * 10

            res_rank += 1
    return -1

rank = -1
max_page = 5

for page in range(max_page):
    html = get_search_html(keyword, page)
    soup = BeautifulSoup(html, 'html.parser')

    title_text = soup.find('title').get_text()
    print(title_text)
    rank = get_page_rank(soup, page)

    page += 1
    if rank != -1:
        break

    time.sleep(3) # アクセス制限対策
    
if rank != -1:
    print("順位: {}位".format(rank))
else:
    print("見つかりませんでした")

ios android シェア - Google 検索
順位: 2位