We Keep Coding

getting an empty list when trying to extract urls from google with beautifulsoup

I am trying to extract the first 100 urls that return from a location search in google
however i am getting an empty list every time ("no results found")
import requests
from bs4 import BeautifulSoup
def get_location_info(location):
query = location + " information"
headers = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.97 Safari/537.36'
}
url = "https://www.google.com/search?q=" + query
response = requests.get(url, headers=headers)
soup = BeautifulSoup(response.text, 'html.parser')
results = soup.find_all("div", class_="r")
websites = []
if results:
counter = 0
for result in results:
websites.append(result.find("a")["href"])
counter += 1
if counter == 100:
break
else:
print("No search results found.")
return websites
location = "Athens"
print(get_location_info(location))
No search results found.
[]
I have also tried this approach :
import requests
from bs4 import BeautifulSoup
def get_location_info(location):
query = location + " information"
headers = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.97 Safari/537.36'
}
url = "https://www.google.com/search?q=" + query
response = requests.get(url, headers=headers)
soup = BeautifulSoup(response.text, 'html.parser')
results = soup.find_all("div", class_="r")
websites = [result.find("a")["href"] for result in results][:10]
return websites
location = "sifnos"
print(get_location_info(location))`
and i get an empty list. I think i am doing everything suggested in similar posts but i still get nothing

Always and first of all, take a look at your soup to see if all the expected ingredients are in place.
Select your elements more specific in this case for example with css selector:
[a.get('href') for a in soup.select('a:has(>h3)')]
To void consent banner also send some cookies:
cookies={'CONSENT':'YES+'}
Example
import requests
from bs4 import BeautifulSoup
def get_location_info(location):
query = location + " information"
headers = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.97 Safari/537.36'
}
url = "https://www.google.com/search?q=" + query
response = requests.get(url, headers=headers, cookies={'CONSENT':'YES+'})
soup = BeautifulSoup(response.text, 'html.parser')
websites = [a.get('href') for a in soup.select('a:has(>h3)')]
return websites
location = "sifnos"
print(get_location_info(location))
Output
['https://www.griechenland.de/sifnos/', 'http://de.sifnos-greece.com/plan-trip-to-sifnos/travel-information.php', 'https://www.sifnosisland.gr/', 'https://www.visitgreece.gr/islands/cyclades/sifnos/', 'http://www.griechenland-insel.de/Hauptseiten/sifnos.htm', 'https://worldonabudget.de/sifnos-griechenland/', 'https://goodmorningworld.de/sifnos-griechenland/', 'https://de.wikipedia.org/wiki/Sifnos', 'https://sifnos.gr/en/sifnos/', 'https://www.discovergreece.com/de/cyclades/sifnos']

Scrape data with <Script type="text/javascript" using beautifulsoup

Im building a web scrape to pull product data from a website, this particular company hides the price behind a "login for Price" banner but the price is hidden in the HTML under <Script type="text/javascript" but im unable to pull it out. the specific link that im testing is https://www.chadwellsupply.com/categories/appliances/Stove-Ranges/hotpoint-24-spacesaver-electric-range---white/
My current code is this and the last line is the one im using to pull the text out.
```
import requests
from bs4 import BeautifulSoup
import pandas as pd
baseurl="https://www.chadwellsupply.com/"
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}
productlinks = []
for x in range (1,3):
response = requests.get(f'https://www.chadwellsupply.com/categories/appliances/Stove-Ranges/?q=&filter=&clearedfilter=undefined&orderby=19&pagesize=24&viewmode=list&currenttab=products&pagenumber={x}&articlepage=')
soup = BeautifulSoup(response.content,'html.parser')
productlist = soup.find_all('div', class_="product-header")
for item in productlist:
for link in item.find_all('a', href = True):
productlinks.append(link['href'])
testlink = 'https://www.chadwellsupply.com/categories/appliances/Stove-Ranges/hotpoint-24-spacesaver-electric-range---white/'
response = requests.get(testlink, headers = headers)
soup = BeautifulSoup(response.content,'html.parser')
print(soup.find('div',class_="product-title").text.strip())
print(soup.find('p',class_="status").text.strip())
print(soup.find('meta',{'property':'og:url'}))
print(soup.find('div',class_="tab-pane fade show active").text.strip())
print(soup.find('div',class_="Chadwell-Shared-Breadcrumbs").text.strip())
print(soup.find('script',{'type':'text/javascript'}).text.strip())
```
Below is the chunk of script from the website (tried to paste directly here but it wouldnt format correctly) that im expecting it to pull but what it gives me is
"window.dataLayer = window.dataLayer || [];"
HTML From website
Ideally id like to just pull the price out but if i can atleast get the whole chunk of data out i can manually extract price.

You can use re/json module to search/parse the HTML data (obviously, beautifulsoup cannot parse JavaScript - another option is to use selenium).
import re
import json
import requests
url = "https://www.chadwellsupply.com/categories/appliances/Stove-Ranges/hotpoint-24-spacesaver-electric-range---white/"
html_doc = requests.get(url).text
data = re.search(r"ga\('ec:addProduct', (.*?)\);", html_doc).group(1)
data = json.loads(data)
print(data)
Prints:
{
"id": "301078",
"name": 'HOTPOINT® 24" SPACESAVER ELECTRIC RANGE - WHITE',
"category": "Stove/ Ranges",
"brand": "Hotpoint",
"price": "759",
}
Then for price you can do:
print(data["price"])
Prints:
759

A hacky alternative to regex is to select for a function in the scripts. In your case, the script contains function(i,s,o,g,r,a,m).
from bs4 import BeautifulSoup
import requests
import json
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}
testlink = 'https://www.chadwellsupply.com/categories/appliances/Stove-Ranges/hotpoint-24-spacesaver-electric-range---white/'
response = requests.get(testlink, headers = headers)
soup = BeautifulSoup(response.content,'html.parser')
for el in soup.find_all("script"):
if "function(i,s,o,g,r,a,m)" in el.text:
scripttext = el.text
You can then select the data.
extracted = scripttext.split("{")[-1].split("}")[0]
my_json = json.loads("{%s}" % extracted)
print(my_json)
#{'id': '301078', 'name': 'HOTPOINT® 24" SPACESAVER ELECTRIC RANGE - WHITE', 'category': 'Stove/ Ranges', 'brand': 'Hotpoint', 'price': '759'}
Then get the price.
print(my_json["price"])
#759

How to get all 'href' with soup in python ? I try so many times but not work

How to get all 'href' with soup in python ? I try so many times but in vain.
Whatever I use 'soup.find' or 'soup.find_all' method to strugle for the 'href', it doesn't work.
python version:3.10
!pip install requests
import requests
import time
import pandas as pd
from bs4 import BeautifulSoup
productlink = []
headers = {'User-Agent':'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Mobile Safari/537.36'}
for page in range(1,2):
url = "https://www.momomall.com.tw/s/103487/dcategory/all/3/{page}"
r = requests.get(url, headers = headers)
Soup = BeautifulSoup(r.text,"lxml")
for link in Soup.find_all('ul',class_="searchItem Stype"):
print(len(link))
Link = link.li.a
LINK = Link.get('href')
print(LINK)
productlink.append(LINK)
print(productlink)

sorry i misunderstood totally your problem. find_all is not a very versatile tool and you were searching for the wrong ul
i barely changed your code but it seems to work now
import requests
import time
import pandas as pd
from bs4 import BeautifulSoup
productlink = []
headers = {'User-Agent':'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Mobile Safari/537.36'}
for page in range(1,2):
url = f"https://www.momomall.com.tw/s/103487/dcategory/all/3/{page}"
r = requests.get(url, headers = headers)
Soup = BeautifulSoup(r.text,"lxml")
for link in Soup.select('ul#surveyContent > li > a[href]:first-of-type'):
print(len(link))
# ~ Link = link.li.a
LINK = link.get('href')
print(LINK)
productlink.append(LINK)
print(productlink)

for page in range(1,2):
url = "https://m.momomall.com.tw/m/store/DCategory.jsp?entp_code=103487&category_code=all&orderby=3&page={}".format(page)
r = requests.get(url,headers = headers)
soup = BeautifulSoup(r.text,'lxml')
for goods_code in soup.select('a.nofollowBtn_star'):
Goods_code = 'https://www.momomall.com.tw/s/103487/'+goods_code.get('goods_code')+'/'
goodlink.append(Goods_code)
for URL in goodlink:
R = requests.get(URL, headers = headers)
Soup = BeautifulSoup(R.text,"lxml")
for dataprice in Soup.select('script'):
import re
discount_regex=re.compile('discountPrice = (\d{1,5})')
print(re.search(discount_regex, dataprice).group(1))
```

Trouble using pandas read_html() : ValueError

from bs4 import BeautifulSoup
from urllib.request import urlopen
import requests
url = "https://finance.naver.com/item/sise_day.nhn?code=068270&page=1"
headers = {'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 11_1_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.141 Safari/537.36'}
res = requests.get(url, verify=True, headers=headers)
with urlopen(url) as doc:
html = BeautifulSoup(res.text, 'lxml')
pgrr = html.find('td', class_='pgRR')
s = str(pgrr.a['href']).split('=')
last_page = s[-1]
df = pd.DataFrame()
sise_url = 'http://finance.naver.com/item/sise_day.nhn?code=068270'
for page in range(1, int(last_page)+1):
page_url = '{}&page={}'.format(sise_url, page)
df = df.append(pd.read_html(page_url, encoding='euc-kr', header='0')[0])
df = df.dropna() # 값이 빠진 행을 제거한다.
print(df)
I'm having this Value error while crawling the Daily stock data in Naver Finance.
I have no trouble getting the url but if i use the read_html() i have Value Error:Table not found issue from the line df = df.append(pd.read_html(page_url, encoding='euc-kr', header='0')[0]). Pls give some advice.

I don't read Korean... however pd.read_html() was getting an error page. Resolved this by requests.get() with headers. Then pass res.text to read_html()
from bs4 import BeautifulSoup
from urllib.request import urlopen
import requests
import pandas as pd
url = "https://finance.naver.com/item/sise_day.nhn?code=068270&page=1"
headers = {'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 11_1_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.141 Safari/537.36'}
res = requests.get(url, verify=True, headers=headers)
with urlopen(url) as doc:
html = BeautifulSoup(res.text, 'lxml')
pgrr = html.find('td', class_='pgRR')
s = str(pgrr.a['href']).split('=')
last_page = s[-1]
df = pd.DataFrame()
sise_url = 'http://finance.naver.com/item/sise_day.nhn?code=068270'
for page in range(1, int(last_page)+1):
page_url = '{}&page={}'.format(sise_url, page)
res = requests.get(page_url, verify=True, headers=headers)
df = df.append(pd.read_html(res.text, encoding='euc-kr')[0])

Web scraping twitter

I want to do web scraping on twitter page to download tweets on a specific search word. I am not able to fetch recursively all the tweets, rather I can fetch 20 tweets. Please help to fetch all the tweets recursively. Below is the code
from bs4 import BeautifulSoup
import requests
import pandas as pd
company_name = 'ABC'
url = 'https://twitter.com/search?q=%23%27%20%20%20' + company_name + '&src=typd&lang=en'
headers = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}
req = requests.get(url, headers=headers);#print(req)
data = req.text;# print(data)
# soup = BeautifulSoup(data, "lxml");# print(soup)
soup = BeautifulSoup(data, "html.parser");# print(soup)
tweets = [p.text for p in soup.findAll('p', class_='tweet-text')]
# print(tweets)
df = pd.DataFrame()
df['Tweet'] = tweets
print(df.head())
print(df.shape)