Das deutsche Python-Forum

Code: Alles auswählen

from bs4 import BeautifulSoup
import requests

url = "http://www.heise.de/"

webpage = requests.get(url).text

soup = BeautifulSoup(webpage, "html.parser")

results = soup.find_all("h2")

for result in results:

	print(result.text.strip(" "))
	
	
import pprint
 
ergebnisse = []
 
results = ["http://www.ard.de", "http://www.zdf.de",
           "http://www.rtl.de", "http://www.disney.de"]
 
for i, result in enumerate(results):
 
    teilergebnis = []
 
    Lead nr = i + 1
    content = "Fahrrad"
    url = result
    cms = "Magento, JTL, Typo3"
    ranking = i
   
    teilergebnis = [Lead nr, content, url, cms, ranking]
   
    ergebnisse.append(teilergebnis)
 
 
pprint.pprint(ergebnisse)

Code: Alles auswählen

from bs4 import BeautifulSoup
import requests
 
url = "http://www.zdf.de/"
 
webpage = requests.get(url).text
 
soup = BeautifulSoup(webpage, "html.parser")
 
results = soup.find_all("h2")
 
for result in results:
 
    print(result.text.strip(" "))
	

	
import pprint
 
ergebnisse = []
 
results = ["http://www.ard.de", "http://www.zdf.de",
           "http://www.rtl.de", "http://www.disney.de"]
 
for i, result in enumerate(results):
 
    teilergebnis = []
 
    nr = i + 1
    content = "Hose, blau"
    url = result
    cms = "Magento, JTL, Typo3"
    ranking = i
   
    teilergebnis = [nr, content, url, cms, ranking]
   
    ergebnisse.append(teilergebnis)
 
 
pprint.pprint(ergebnisse)

Code: Alles auswählen

import requests
from bs4 import BeautifulSoup

suchwort = "Python crawler"

url = "https://www.google.de/search?q={}"

# URL zusammenbauen
google_url = url.format(suchwort.replace(" ", "+"))

# Seite abfragen
webpage = requests.get(google_url).text

soup = BeautifulSoup(webpage, "html.parser")

with open("webpage.txt", "w") as f:
    f.write(webpage)

"""
Text

Welcome to Python.org
https://www.python.org/ Diese Seite übersetzen
The official home of the Python Programming Language.
‎Download - ‎Python 3.4.3 - ‎Documentation - ‎Getting Started

HTML in Auswahl (scheint nicht (!) zu stimmen!!!)

<div class="rc" data-hveid="31">
<h3 class="r"><a href="[...] data-href="https://www.python.org/">Welcome to Python.org</a></h3>
<div class="s"><div><div class="f kv _SWb" style="white-space:nowrap">
<cite class="_Rm">https://www.<b>python</b>.org/</cite>
[...]
<span class="st">The official home of the <em>Python</em> Programming Language.</span>
[...]
"""

results = soup.find_all("li", attrs={"class": "g"})

ergebnisse = []

for i, result in enumerate(results):
    # print(result)

    print("Rang:", i+1)
    
    title = result.find("h3").find("a").text.replace("\n", "\t")
    print(title)

    """
    <span class="st">PyPI Version PyPI monthly downloads Wheel Status <b>Python</b> 3 Porting Status <br>
    Coverage report. Install the latest version of Scrapy. Scrapy 1.0. pip install scrapy.</br></span>
    """
    summary = result.find("span", attrs={"class": "st"}).text.replace("\n", "\t")
    print(summary)

    # input(">>>")
    ergebnisse.append([i+1, title, summary])
    
with open("ergebnisse.csv", "a") as f:
    for zeile in ergebnisse:
        f.write(";".join(map(str, zeile))+"\n")