jonas/birdscrape
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Updated README.md

Browse Source
This commit is contained in:
jonas
2021-01-10 12:39:31 +00:00
parent 4683157078
commit 8b49606392
1 changed files with 2 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
birdscrape.py
View File

@@ -33,22 +33,18 @@ print("Getting list of all illustrated birds on: " + URL)
for bird in birdlist.findAll('li'): for bird in birdlist.findAll('li'):
bird_url = "http://tirill.de/" + bird.a['href'] bird_url = "http://tirill.de/" + bird.a['href']
#print(bird_url)
bird_dict_urls["URL"].append(bird_url) bird_dict_urls["URL"].append(bird_url)
print(str(len(bird_dict_urls["URL"])) + " Vochels gefunden.") print(str(len(bird_dict_urls["URL"])) + " Vochels found.")
for i in bird_dict_urls["URL"]: for i in bird_dict_urls["URL"]:
## SING BIRD INFO + DOWNLOAD ## Single bird info + download
html_bird = requests.get(i) html_bird = requests.get(i)
bird_soup = BeautifulSoup(html_bird.text, 'html.parser') bird_soup = BeautifulSoup(html_bird.text, 'html.parser')
bird_images_container = bird_soup.find_all('figure', class_ = "image_container") bird_images_container = bird_soup.find_all('figure', class_ = "image_container")
#print(bird_images_container)
for image in bird_images_container: for image in bird_images_container:
#print(image.img['alt'])
#print(image.img['src'])
full_path_img = "https://tirill.de/" + image.img['src'] full_path_img = "https://tirill.de/" + image.img['src']
filename = full_path_img.split("/")[-1] filename = full_path_img.split("/")[-1]
print(full_path_img) print(full_path_img)